Tootfinder

Buyer's Agent Networks Podcast
Great Australian Pods Podcast Directory: #GreatAusPods

Kritische Sicherheitslücke in Microsoft 365 Copilot zeigt Risiko von KI-Agenten
Der KI-Agent von M365 konnte per E-Mail und ohne Mausklick zur Freigabe sensibler Informationen verführt werden. Microsoft hat die Lücke jetzt geschlossen.

VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
Li Kang, Xiufeng Song, Heng Zhou, Yiran Qin, Jie Yang, Xiaohong Liu, Philip Torr, Lei Bai, Zhenfei Yin
https://arxiv.org/abs/2506.09049

VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
Coordinating multiple embodied agents in dynamic environments remains a core challenge in artificial intelligence, requiring both perception-driven reasoning and scalable cooperation strategies. While recent works have leveraged large language models (LLMs) for multi-agent planning, a few have begun to explore vision-language models (VLMs) for visual reasoning. However, these VLM-based approaches remain limited in their support for diverse embodiment types. In this work, we introduce VIKI-Bench…

HiBerNAC: Hierarchical Brain-emulated Robotic Neural Agent Collective for Disentangling Complex Manipulation
Hongjun Wu, Heng Zhang, Pengsong Zhang, Jin Wang, Cong Wang
https://arxiv.org/abs/2506.08296

HiBerNAC: Hierarchical Brain-emulated Robotic Neural Agent Collective for Disentangling Complex Manipulation
Recent advances in multimodal vision-language-action (VLA) models have revolutionized traditional robot learning, enabling systems to interpret vision, language, and action in unified frameworks for complex task planning. However, mastering complex manipulation tasks remains an open challenge, constrained by limitations in persistent contextual memory, multi-agent coordination under uncertainty, and dynamic long-horizon planning across variable sequences. To address this challenge, we propose \…

LA man faces 8 years in prison for ‘spitting at an ICE agent’ after being charged with assaulting a federal employee | The Independent
https://www.the-independent.com/news/world/americas/crime/los-angeles-arrest-spitting-ice-agent-face-b2768986.html

Anomaly, Class Division, and Decoupling in Wealth Dynamics
Jaeseok Hur, Meesoon Ha, Hawoong Jeong
https://arxiv.org/abs/2506.08175 https://

Anomaly, Class Division, and Decoupling in Wealth Dynamics
Economic inequality is shaped by the agent-network structure, the interaction between agents, and the individual agent's ability. We provide a comprehensive picture of anomalous diffusion, economic class division, and bimodal wealth distribution in an agent-based model, where the allocation of heterogeneous agent abilities/growth rates is tuned in sparse regular networks.In particular, we focus on the statistical characteristics of logarithmic scaled normalized wealth distributions with two abi…

Agent-based Condition Monitoring Assistance with Multimodal Industrial Database Retrieval Augmented Generation
Karl L\"owenmark, Daniel Str\"ombergsson, Chang Liu, Marcus Liwicki, Fredrik Sandin
https://arxiv.org/abs/2506.09247

Agent-based Condition Monitoring Assistance with Multimodal Industrial Database Retrieval Augmented Generation
Condition monitoring (CM) plays a crucial role in ensuring reliability and efficiency in the process industry. Although computerised maintenance systems effectively detect and classify faults, tasks like fault severity estimation, and maintenance decisions still largely depend on human expert analysis. The analysis and decision making automatically performed by current systems typically exhibit considerable uncertainty and high false alarm rates, leading to increased workload and reduced effici…

Agent's Take: Inside the Bengals' contract issues with Trey Hendrickson and why there's no clear end in sight

https://www.cbssports.…

Researchers find the first known "zero-click" attack on an AI agent; the now-fixed flaw in Microsoft 365 Copilot would let a hacker attack a user via an email (Sharon Goldman/Fortune)
https://fortune.com/2025/06/11/microsoft-cop…

Exclusive: New Microsoft Copilot flaw signals broader risk of AI agents being hacked—‘I would be terrified’
Microsoft fixed the Copilot flaw, but researchers warn the real danger lies in how all AI agents are built.

Your Agent Can Defend Itself against Backdoor Attacks
Li Changjiang, Liang Jiacheng, Cao Bochuan, Chen Jinghui, Wang Ting
https://arxiv.org/abs/2506.08336 …

Your Agent Can Defend Itself against Backdoor Attacks
Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to execute malicious operations when presented with specific triggers in their inputs or environments. To address this pressing risk, we present ReAgent, a novel defense against a range of backdoor attacks on LLM-based agents. Intuitively, backdoor attacks often res…

« J'ai découvert le support SSH agent de Bitwarden et ses conséquences sur l'utilisation de Age »
#TIL

2nd-year UDFA with huge bonus may be shaking up Cowboys starting lineup during minicamp https://cowboyswire.usatoday.com/story/sports/nfl/cowboys/2025/06/…

I just saw a post saying someone let their agent AI run for 19 hours to solve a problem.
Is that the expectation?
I’m going to predict a future scandal: A global consulting firm has been caught charging human hours for agentic AI elapsed time. If I were an unscrupulous consulting firm, I could charge customers 24 hours a day at ludicrously high prices to deliver what likely would have been an ill-advised and doomed project anyway.

FAIRTOPIA: Envisioning Multi-Agent Guardianship for Disrupting Unfair AI Pipelines
Athena Vakali, Ilias Dimitriadis
https://arxiv.org/abs/2506.09107 https:…

FAIRTOPIA: Envisioning Multi-Agent Guardianship for Disrupting Unfair AI Pipelines
AI models have become active decision makers, often acting without human supervision. The rapid advancement of AI technology has already caused harmful incidents that have hurt individuals and societies and AI unfairness in heavily criticized. It is urgent to disrupt AI pipelines which largely neglect human principles and focus on computational biases exploration at the data (pre), model(in), and deployment (post) processing stages. We claim that by exploiting the advances of agents technology,…

MasHost Builds It All: Autonomous Multi-Agent System Directed by Reinforcement Learning
Kuo Yang, Xingjie Yang, Linhui Yu, Qing Xu, Yan Fang, Xu Wang, Zhengyang Zhou, Yang Wang
https://arxiv.org/abs/2506.08507

MasHost Builds It All: Autonomous Multi-Agent System Directed by Reinforcement Learning
Large Language Model (LLM)-driven Multi-agent systems (Mas) have recently emerged as a powerful paradigm for tackling complex real-world tasks. However, existing Mas construction methods typically rely on manually crafted interaction mechanisms or heuristic rules, introducing human biases and constraining the autonomous ability. Even with recent advances in adaptive Mas construction, existing systems largely remain within the paradigm of semi-autonomous patterns. In this work, we propose MasHos…

This https://arxiv.org/abs/2506.02841 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Ensemble-MIX: Enhancing Sample Efficiency in Multi-Agent RL Using Ensemble Methods
Multi-agent reinforcement learning (MARL) methods have achieved state-of-the-art results on a range of multi-agent tasks. Yet, MARL algorithms typically require significantly more environment interactions than their single-agent counterparts to converge, a problem exacerbated by the difficulty in exploring over a large joint action space and the high variance intrinsic to MARL environments. To tackle these issues, we propose a novel algorithm that combines a decomposed centralized critic with d…

The Raiders are hoping to get a 2-for-1 deal with their top free agent addition https://raiderswire.usatoday.com/story/sports/nfl/raiders/2025/06/09/raiders-versatile-db-jerem…

LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization
Jiaqi Tang, Yu Xia, Yi-Feng Wu, Yuwei Hu, Yuhui Chen, Qing-Guo Chen, Xiaogang Xu, Xiangyu Wu, Hao Lu, Yanqing Ma, Shiyin Lu, Qifeng Chen
https://arxiv.org/abs/2506.09373

LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization
The advent of autonomous agents is transforming interactions with Graphical User Interfaces (GUIs) by employing natural language as a powerful intermediary. Despite the predominance of Supervised Fine-Tuning (SFT) methods in current GUI agents for achieving spatial localization, these methods face substantial challenges due to their limited capacity to accurately perceive positional data. Existing strategies, such as reinforcement learning, often fail to assess positional accuracy effectively, …

Survey of LLM Agent Communication with MCP: A Software Design Pattern Centric Review
Anjana Sarkar, Soumyendu Sarkar
https://arxiv.org/abs/2506.05364 https…

Survey of LLM Agent Communication with MCP: A Software Design Pattern Centric Review
This survey investigates how classical software design patterns can enhance the reliability and scalability of communication in Large Language Model (LLM)-driven agentic AI systems, focusing particularly on the Model Context Protocol (MCP). It examines the foundational architectures of LLM-based agents and their evolution from isolated operation to sophisticated, multi-agent collaboration, addressing key communication hurdles that arise in this transition. The study revisits well-established pa…

AI doesn't make you more efficient:
Thoughts after a year of working with LLMs and building Agent
Since everyone is in the business of giving their opinion on the whole AI craze at the moment I thought I’d throw mine out in the ether. […]
👉 https://byt3bl33d3r.substack.com/p/…

AI doesn't make you more efficient
Thoughts after a year of working with LLMs and building Agents

Is Talanoa Hufanga the next great Broncos safety? https://www.espn.com/nfl/story/_/id/45480888/broncos-safety-talanoa-hufanga-free-agent-signing-excitement-injuries-fit

Patterns of Patterns III
Joseph Corneli, Charles J. Danoff, Raymond S. Puzio, Sridevi Ayloo, Serge Belich, Mary Tedeschi
https://arxiv.org/abs/2506.09696 h…

Patterns of Patterns III
Building on earlier installments, this paper re-examines the PLACARD pattern. We report on a series of workshops where PLACARD was used to scaffold collaborative reflection, speculative inquiry, and stimulate design pattern generation. These accounts are enriched by a comparison case: virtual workshops carried out with simple AI-based chatbots. We discuss limitations and lessons learned from both the human and multi-agent settings. We conclude by outlining a future development strategy at the i…

Marines are highly trained in combat and crisis response, with time in conflict zones like Syria and Afghanistan.
But that is starkly different from the role they will face now:
They could potentially be hit by L A hipsters carrying gas canisters and have to quickly decide how to respond
or face decisions about protecting an immigration enforcement agent from crowds.

Pentagon draws up rules for Marines deployed to LA protests
The Pentagon is scrambling to establish rules to guide U.S. Marines who could be faced with the rare and difficult prospect of using force against citizens on American soil, now that the Trump administration is deploying active duty troops to the immigration raid protests in Los Angeles. U.S. Northern Command said Monday that it's sending 700 Marines into the Los Angeles area to protect federal property and personnel. A U.S. official says troops will be armed with their normal service weapons b…

Should the Dallas Cowboys target top NFL free agent Asante Samuel Jr? https://www.si.com/nfl/cowboys/news/should-dallas-cowboys-target-top-nfl-free-agent-asante-samuel-jr

This https://arxiv.org/abs/2410.08850 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Learning to Stop: Deep Learning for Mean Field Optimal Stopping
Optimal stopping is a fundamental problem in optimization with applications in risk management, finance, robotics, and machine learning. We extend the standard framework to a multi-agent setting, named multi-agent optimal stopping (MAOS), where agents cooperate to make optimal stopping decisions in a finite-space, discrete-time environment. Since solving MAOS becomes computationally prohibitive as the number of agents is very large, we study the mean-field optimal stopping (MFOS) problem, obtai…

Reinforcement Fine-Tuning for Reasoning towards Multi-Step Multi-Source Search in Large Language Models
Wentao Shi, Yiqing Shen
https://arxiv.org/abs/2506.08352

Reinforcement Fine-Tuning for Reasoning towards Multi-Step Multi-Source Search in Large Language Models
Large language models (LLMs) can face factual limitations when responding to time-sensitive queries about recent events that arise after their knowledge thresholds in the training corpus. Existing search-augmented approaches fall into two categories, each with distinct limitations: multi-agent search frameworks incur substantial computational overhead by separating search planning and response synthesis across multiple LLMs, while single-LLM tool-calling methods restrict themselves to sequentia…

AI Agent Behavioral Science
Lin Chen, Yunke Zhang, Jie Feng, Haoye Chai, Honglin Zhang, Bingbing Fan, Yibo Ma, Shiyuan Zhang, Nian Li, Tianhui Liu, Nicholas Sukiennik, Keyu Zhao, Yu Li, Ziyi Liu, Fengli Xu, Yong Li
https://arxiv.org/abs/2506.06366

AI Agent Behavioral Science
Recent advances in large language models (LLMs) have enabled AI systems to behave in increasingly human-like ways, exhibiting planning, adaptation, and social dynamics across increasingly diverse, interactive, and open-ended scenarios. These behaviors are not solely the product of the models' internal architecture, but emerge from their integration into agentic systems that operate within situated contexts, where goals, feedback, and interactions shape behavior over time. This shift calls for a…

Chinese startups and tech giants are racing to create AI agents for both local and global consumers, following the popularity of Butterfly Effect's Manus (Caiwei Chen/MIT Technology Review)
https://www.technologyreview.com/2025/06/05/1117958/china-ai-a…

Manus has kick-started an AI agent boom in China
A stampede of contenders and copycats has followed the launch of the general AI agent, but China’s internet restrictions have so far made it easier to cater to overseas users.

G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
Guibin Zhang, Muxin Fu, Guancheng Wan, Miao Yu, Kun Wang, Shuicheng Yan
https://arxiv.org/abs/2506.07398

G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
Large language model (LLM)-powered multi-agent systems (MAS) have demonstrated cognitive and execution capabilities that far exceed those of single LLM agents, yet their capacity for self-evolution remains hampered by underdeveloped memory architectures. Upon close inspection, we are alarmed to discover that prevailing MAS memory mechanisms (1) are overly simplistic, completely disregarding the nuanced inter-agent collaboration trajectories, and (2) lack cross-trial and agent-specific customiza…

Delegation with Costly Inspection
Mohammad T. Hajiaghayi, Piotr Krysta, Mohammad Mahdavi, Suho Shin
https://arxiv.org/abs/2506.07162 https://

Delegation with Costly Inspection
We study the problem of delegated choice with inspection cost (DCIC), which is a variant of the delegated choice problem by Kleinberg and Kleinberg (EC'18) as well as an extension of the Pandora's box problem with nonobligatory inspection (PNOI) by Doval (JET'18). In our model, an agent may strategically misreport the proposed element's utility, unlike the standard delegated choice problem which assumes that the agent truthfully reports the utility for the proposed alternative. Thus, the princi…

Towards AI-assisted Neutrino Flavor Theory Design
Jason Benjamin Baretz, Max Fieg, Vijay Ganesh, Aishik Ghosh, V. Knapp-Perez, Jake Rudolph, Daniel Whiteson
https://arxiv.org/abs/2506.08080

Towards AI-assisted Neutrino Flavor Theory Design
Particle physics theories, such as those which explain neutrino flavor mixing, arise from a vast landscape of model-building possibilities. A model's construction typically relies on the intuition of theorists. It also requires considerable effort to identify appropriate symmetry groups, assign field representations, and extract predictions for comparison with experimental data. We develop an Autonomous Model Builder (AMBer), a framework in which a reinforcement learning agent interacts with a …

Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning
Haochen Zhang, Zhong Zheng, Lingzhou Xue
https://arxiv.org/abs/2506.04626

Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning
Motivated by real-world settings where data collection and policy deployment -- whether for a single agent or across multiple agents -- are costly, we study the problem of on-policy single-agent reinforcement learning (RL) and federated RL (FRL) with a focus on minimizing burn-in costs (the sample sizes needed to reach near-optimal regret) and policy switching or communication costs. In parallel finite-horizon episodic Markov Decision Processes (MDPs) with $S$ states and $A$ actions, existing m…

Deep Equivariant Multi-Agent Control Barrier Functions
Nikolaos Bousias, Lars Lindemann, George Pappas
https://arxiv.org/abs/2506.07755 https://

Deep Equivariant Multi-Agent Control Barrier Functions
With multi-agent systems increasingly deployed autonomously at scale in complex environments, ensuring safety of the data-driven policies is critical. Control Barrier Functions have emerged as an effective tool for enforcing safety constraints, yet existing learning-based methods often lack in scalability, generalization and sampling efficiency as they overlook inherent geometric structures of the system. To address this gap, we introduce symmetries-infused distributed Control Barrier Functions…

This https://arxiv.org/abs/2503.24078 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

A Complete Mental Temporal Logic for Intelligent Agent
In this paper, we present a complete mental temporal logic, called BPICTL, which generalizes CTL by introducing mental modalities. A sound and complete inference system of BPICTL is given. We prove the finite model property of BPICTL. Furthermore, we present a model checking algorithm for BPICTL.

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new/
[5/5]:
AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation

Ego-centric Learning of Communicative World Models for Autonomous Driving
Hang Wang, Dechen Gao, Junshan Zhang
https://arxiv.org/abs/2506.08149 https://

Ego-centric Learning of Communicative World Models for Autonomous Driving
We study multi-agent reinforcement learning (MARL) for tasks in complex high-dimensional environments, such as autonomous driving. MARL is known to suffer from the \textit{partial observability} and \textit{non-stationarity} issues. To tackle these challenges, information sharing is often employed, which however faces major hurdles in practice, including overwhelming communication overhead and scalability concerns. By making use of generative AI embodied in world model together with its latent …

This https://arxiv.org/abs/2505.11963 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

MARVEL: Multi-Agent RTL Vulnerability Extraction using Large Language Models
Hardware security verification is a challenging and time-consuming task. For this purpose, design engineers may utilize tools such as formal verification, linters, and functional simulation tests, coupled with analysis and a deep understanding of the hardware design being inspected. Large Language Models (LLMs) have been used to assist during this task, either directly or in conjunction with existing tools. We improve the state of the art by proposing MARVEL, a multi-agent LLM framework for a u…

This https://arxiv.org/abs/2505.22942 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning
Large language models (LLMs)-empowered web agents enables automating complex, real-time web navigation tasks in enterprise environments. However, existing web agents relying on supervised fine-tuning (SFT) often struggle with generalization and robustness due to insufficient reasoning capabilities when handling the inherently dynamic nature of web interactions. In this study, we introduce WorkForceAgent-R1, an LLM-based web agent trained using a rule-based R1-style reinforcement learning framew…

Las Vegas Raiders Connected to Star Linebacker Who Just Hit Free Agency https://heavy.com/sports/nfl/las-vegas-raiders/connected-to-free-agent-star-linebacker/?adt_ei=[email]

Understanding Software Engineering Agents Through the Lens of Traceability: An Empirical Study
Ira Ceka, Saurabh Pujar, Shyam Ramji, Luca Buratti, Gail Kaiser, Baishakhi Ray
https://arxiv.org/abs/2506.08311

Understanding Software Engineering Agents Through the Lens of Traceability: An Empirical Study
With the advent of large language models (LLMs), software engineering agents (SWE agents) have emerged as a powerful paradigm for automating a range of software tasks -- from code generation and repair to test case synthesis. These agents operate autonomously by interpreting user input and responding to environmental feedback. While various agent architectures have demonstrated strong empirical performance, the internal decision-making worfklows that drive their behavior remain poorly understoo…

Simulating nationwide coupled disease and fear spread in an agent-based model
Joy Kitson, Prescott C. Alexander, Joseph Tuccillo, Abhinav Bhatele, Sara Y. Del Valle, Timothy C. Germann
https://arxiv.org/abs/2506.07842

Simulating nationwide coupled disease and fear spread in an agent-based model
Human behavior and disease spread evolve together over the course of any disease outbreak. We present a dynamic model of that relationship based on the coupled spread of a disease and fear of that disease, and implement this model in a simulator, EpiCast, that simulates disease spread between individuals in a realistic synthetic population. In our model, fear of the disease spreads through both in-person contact and broadcast media, driving people to adopt behaviors that reduce disease spread. …

OpenAI updates its coding agent Codex with internet access, turned off by default, and expands availability to ChatGPT Plus users (Simon Willison/Simon Willison's Weblog)
https://simonwillison.net/2025/Jun/3/codex-agent-internet-access/

Codex agent internet access
Sam Altman, [just now](https://twitter.com/sama/status/1930006856019390521): > codex gets access to the internet today! it is off by default and there are complex tradeoffs; people should read about the risks carefully and …

Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs
\v{S}imon Sedl\'a\v{c}ek, Bolaji Yusuf, J\'an \v{S}vec, Pradyoth Hegde, Santosh Kesiraju, Old\v{r}ich Plchot, Jan \v{C}ernock\'y
https://arxiv.org/abs/2506.08633

Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs
In this work, we approach spoken Dialogue State Tracking (DST) by bridging the representation spaces of speech encoders and LLMs via a small connector module, with a focus on fully open-sourced and open-data components (WavLM-large, OLMo). We focus on ablating different aspects of such systems including full/LoRA adapter fine-tuning, the effect of agent turns in the dialogue history, as well as fuzzy matching-based output post-processing, which greatly improves performance of our systems on nam…

Learn as Individuals, Evolve as a Team: Multi-agent LLMs Adaptation in Embodied Environments
Xinran Li, Chenjia Bai, Zijian Li, Jiakun Zheng, Ting Xiao, Jun Zhang
https://arxiv.org/abs/2506.07232

Learn as Individuals, Evolve as a Team: Multi-agent LLMs Adaptation in Embodied Environments
Large language models (LLMs) possess extensive knowledge bases and strong reasoning capabilities, making them promising tools for complex, multi-agent planning in embodied environments. However, despite LLMs' advanced abilities and the sophisticated modular design of agentic methods, existing LLM-based planning algorithms remain limited by weak adaptation capabilities to multi-agent embodied scenarios. We address this limitation by introducing a framework that enables LLM agents to learn and ev…

Mack says $18M Chargers extension made sense https://www.espn.com/nfl/story/_/id/45495317/khalil-mack-los-angeles-chargers-extension

Learning The Minimum Action Distance
Lorenzo Steccanella, Joshua B. Evans, \"Ozg\"ur \c{S}im\c{s}ek, Anders Jonsson
https://arxiv.org/abs/2506.09276

Learning The Minimum Action Distance
This paper presents a state representation framework for Markov decision processes (MDPs) that can be learned solely from state trajectories, requiring neither reward signals nor the actions executed by the agent. We propose learning the minimum action distance (MAD), defined as the minimum number of actions required to transition between states, as a fundamental metric that captures the underlying structure of an environment. MAD naturally enables critical downstream tasks such as goal-conditi…

#GitHub #Copilot coding agent in public preview
https://github.blog/changelog/2025-…

Distributed Asynchronous Primal-Dual Optimization for Supply-Chain Networks
Laksh Patel, Neel Shanbhag
https://arxiv.org/abs/2506.08024 https://

Distributed Asynchronous Primal-Dual Optimization for Supply-Chain Networks
Distributed supply-chain optimization demands algorithms that can cope with unreliable communication, unbounded messaging delays, and geographically dispersed agents while still guaranteeing convergence with provable rates. In this work, we introduce DAPD-SCO (Distributed Asynchronous Primal-Dual Optimization for Supply-Chain Networks), a fully asynchronous primal-dual scheme for network flow allocation over directed acyclic supply-chain graphs. Each edge agent independently updates its local f…

Automatic Treatment Planning using Reinforcement Learning for High-dose-rate Prostate Brachytherapy
Tonghe Wang, Yining Feng, Xiaofeng Yang
https://arxiv.org/abs/2506.09805

Automatic Treatment Planning using Reinforcement Learning for High-dose-rate Prostate Brachytherapy
Purpose: In high-dose-rate (HDR) prostate brachytherapy procedures, the pattern of needle placement solely relies on physician experience. We investigated the feasibility of using reinforcement learning (RL) to provide needle positions and dwell times based on patient anatomy during pre-planning stage. This approach would reduce procedure time and ensure consistent plan quality. Materials and Methods: We train a RL agent to adjust the position of one selected needle and all the dwell times on i…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new/
[1/5]:
FREIDA: A Framework for developing quantitative agent based models based on qualitative expert kn...

Geometric Hyperscanning under Active Inference
Nicolas Hinrichs, Mahault Albarracin, Dimitris Bolis, Yuyue Jiang, Leonardo Christov-Moore, Leonhard Schilbach
https://arxiv.org/abs/2506.08599

Geometric Hyperscanning under Active Inference
Second-person neuroscience holds social cognition as embodied meaning co-regulation through reciprocal interaction, modeled here as coupled active inference with affect emerging as inference over identity-relevant surprise. Each agent maintains a self-model that tracks violations in its predictive coherence while recursively modeling the other. Valence is computed from self-model prediction error, weighted by self-relevance, and modulated by prior affective states and by what we term temporal a…

Germaine Pratt signs with Raiders instantly becoming their highest plaid linebacker https://raiderswire.usatoday.com/story/sports/nfl/raiders/2025/06/11/raiders-sign-lb-germaine-pratt-benga…

‘Plausible’ Chance Cowboys Part Ways With $3 Million Free Agent RB https://heavy.com/sports/nfl/dallas-cowboys/part-ways-free-agent-javonte-williams/?adt_ei=[email]

Sequence Modeling for N-Agent Ad Hoc Teamwork
Caroline Wang, Di Yang Shi, Elad Liebman, Ishan Durugkar, Arrasy Rahman, Peter Stone
https://arxiv.org/abs/2506.05527

Sequence Modeling for N-Agent Ad Hoc Teamwork
N-agent ad hoc teamwork (NAHT) is a newly introduced challenge in multi-agent reinforcement learning, where controlled subteams of varying sizes must dynamically collaborate with varying numbers and types of unknown teammates without pre-coordination. The existing learning algorithm (POAM) considers only independent learning for its flexibility in dealing with a changing number of agents. However, independent learning fails to fully capture the inter-agent dynamics essential for effective colla…

Distributed Risk-Sensitive Safety Filters for Uncertain Discrete-Time Systems
Armin Lederer, Erfaun Noorani, Andreas Krause
https://arxiv.org/abs/2506.07347

Distributed Risk-Sensitive Safety Filters for Uncertain Discrete-Time Systems
Ensuring safety in multi-agent systems is a significant challenge, particularly in settings where centralized coordination is impractical. In this work, we propose a novel risk-sensitive safety filter for discrete-time multi-agent systems with uncertain dynamics that leverages control barrier functions (CBFs) defined through value functions. Our approach relies on centralized risk-sensitive safety conditions based on exponential risk operators to ensure robustness against model uncertainties. W…

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt
Zhilong Wang, Neha Nagaraja, Lan Zhang, Hayretdin Bahsi, Pawan Patil, Peng Liu
https://arxiv.org/abs/2506.05739

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt
LLM agents are widely used as agents for customer support, content generation, and code assistance. However, they are vulnerable to prompt injection attacks, where adversarial inputs manipulate the model's behavior. Traditional defenses like input sanitization, guard models, and guardrails are either cumbersome or ineffective. In this paper, we propose a novel, lightweight defense mechanism called Polymorphic Prompt Assembling (PPA), which protects against prompt injection with near-zero overhe…

Agent Interpolation for Knowledge
Marta B\'ilkov\'a, Wesley Fussner, Roman Kuznets
https://arxiv.org/abs/2505.23401 https://a…

Agent Interpolation for Knowledge
We define a new type of proof formalism for multi-agent modal logics with S5-type modalities. This novel formalism combines the features of hypersequents to represent S5 modalities with nested sequents to represent the T-like modality alternations. We show that the calculus is sound and complete, cut-free, and terminating and yields decidability and the finite model property for multi-agent S5. We also use it to prove the Lyndon (and hence Craig) interpolation property for multi-agent S5, consi…

This https://arxiv.org/abs/2505.05660 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

Not Like Us, Hunty: Measuring Perceptions and Behavioral Effects of Minoritized Anthropomorphic Cues in LLMs
As large language models (LLMs) increasingly adapt and personalize to diverse sets of users, there is an increased risk of systems appropriating sociolects, i.e., language styles or dialects that are associated with specific minoritized lived experiences (e.g., African American English, Queer slang). In this work, we examine whether sociolect usage by an LLM agent affects user reliance on its outputs and user perception (satisfaction, frustration, trust, and social presence). We designed and co…

Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals
Junyan Liu, Arnab Maiti, Artin Tajdini, Kevin Jamieson, Lillian J. Ratliff
https://arxiv.org/abs/2505.23124

Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals
We initiate the study of a repeated principal-agent problem over a finite horizon $T$, where a principal sequentially interacts with $K\geq 2$ types of agents arriving in an adversarial order. At each round, the principal strategically chooses one of the $N$ arms to incentivize for an arriving agent of unknown type. The agent then chooses an arm based on its own utility and the provided incentive, and the principal receives a corresponding reward. The objective is to minimize regret against the…

Preference-based learning for news headline recommendation
Alexandre Bouras, Audrey Durand, Richard Khoury
https://arxiv.org/abs/2506.06334 https://…

Preference-based learning for news headline recommendation
This study explores strategies for optimizing news headline recommendations through preference-based learning. Using real-world data of user interactions with French-language online news posts, we learn a headline recommender agent under a contextual bandit setting. This allows us to explore the impact of translation on engagement predictions, as well as the benefits of different interactive strategies on user engagement during data collection. Our results show that explicit exploration may not…

This https://arxiv.org/abs/2506.02943 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

A Multi-agent LLM-based JUit Test Generation with Strong Oracles
Unit testing plays a critical role in ensuring software correctness. However, writing unit tests manually is laborious, especially for strong typed languages like Java, motivating the need for automated approaches. Traditional methods primarily rely on search-based or randomized algorithms to generate tests that achieve high code coverage and produce regression oracles, which are derived from the program's current behavior rather than its intended functionality. Recent advances in large languag…

Decentralized Optimization with Amplified Privacy via Efficient Communication
Wei Huo, Changxin Liu, Kemi Ding, Karl Henrik Johansson, Ling Shi
https://arxiv.org/abs/2506.07102

Decentralized Optimization with Amplified Privacy via Efficient Communication
Decentralized optimization is crucial for multi-agent systems, with significant concerns about communication efficiency and privacy. This paper explores the role of efficient communication in decentralized stochastic gradient descent algorithms for enhancing privacy preservation. We develop a novel algorithm that incorporates two key features: random agent activation and sparsified communication. Utilizing differential privacy, we demonstrate that these features reduce noise without sacrificing…

AI-Generated Compromises for Coalition Formation
Eyal Briman, Ehud Shapiro, Nimrod Talmon
https://arxiv.org/abs/2506.06837 https://ar…

AI-Generated Compromises for Coalition Formation
The challenge of finding compromises between agent proposals is fundamental to AI subfields such as argumentation, mediation, and negotiation. Building on this tradition, Elkind et al. (2021) introduced a process for coalition formation that seeks majority-supported proposals preferable to the status quo, using a metric space where each agent has an ideal point. A crucial step in this process involves identifying compromise proposals around which agent coalitions can unite. How to effectively f…

One Free Agent Signing The Las Vegas Raiders Would Greatly Benefit From https://raiderramble.com/2025/06/03/one-free-agent-las-vegas-raiders-would-greatly-benefit-from/

This https://arxiv.org/abs/2410.04444 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement
The rapid advancement of large language models (LLMs) has significantly enhanced the capabilities of AI-driven agents across various tasks. However, existing agentic systems, whether based on fixed pipeline algorithms or pre-defined meta-learning frameworks, cannot search the whole agent design space due to the restriction of human-designed components, and thus might miss the globally optimal agent design. In this paper, we introduce Gödel Agent, a self-evolving framework inspired by the Göde…

OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis
Junting Chen, Haotian Liang, Lingxiao Du, Weiyun Wang, Mengkang Hu, Yao Mu, Wenhai Wang, Jifeng Dai, Ping Luo, Wenqi Shao, Lin Shao
https://arxiv.org/abs/2506.04217

OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis
The rapid progress of navigation, manipulation, and vision models has made mobile manipulators capable in many specialized tasks. However, the open-world mobile manipulation (OWMM) task remains a challenge due to the need for generalization to open-ended instructions and environments, as well as the systematic complexity to integrate high-level decision making with low-level robot control based on both global scene understanding and current agent state. To address this complexity, we propose a …

This https://arxiv.org/abs/2505.00546 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Directly Forecasting Belief for Reinforcement Learning with Delays
Reinforcement learning (RL) with delays is challenging as sensory perceptions lag behind the actual events: the RL agent needs to estimate the real state of its environment based on past observations. State-of-the-art (SOTA) methods typically employ recursive, step-by-step forecasting of states. This can cause the accumulation of compounding errors. To tackle this problem, our novel belief estimation method, named Directly Forecasting Belief Transformer (DFBT), directly forecasts states from ob…

This https://arxiv.org/abs/2502.14847 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Red-Teaming LLM Multi-Agent Systems via Communication Attacks
Large Language Model-based Multi-Agent Systems (LLM-MAS) have revolutionized complex problem-solving capability by enabling sophisticated agent collaboration through message-based communications. While the communication framework is crucial for agent coordination, it also introduces a critical yet unexplored security vulnerability. In this work, we introduce Agent-in-the-Middle (AiTM), a novel attack that exploits the fundamental communication mechanisms in LLM-MAS by intercepting and manipulat…

Steelers not expected to trade for Jonnu Smith, per report, agent says TE wants to remain with Dolphins

https://www.cbssports.com/nfl/news/steeler…

This https://arxiv.org/abs/2502.06994 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering
Software engineering (SE) is increasingly collaborative, with developers working together on shared complex codebases. Effective collaboration in shared environments requires participants -- whether humans or AI agents -- to stay on the same page as their environment evolves. When a collaborator's understanding diverges from the current state -- what we term the out-of-sync challenge -- the collaborator's actions may fail, leading to integration issues. In this work, we introduce SyncMind, a fr…

Mapping Student-AI Interaction Dynamics in Multi-Agent Learning Environments: Supporting Personalised Learning and Reducing Performance Gaps
Zhanxin Hao, Jie Cao, Ruimiao Li, Jifan Yu, Zhiyuan Liu, Yu Zhang
https://arxiv.org/abs/2506.02993

Mapping Student-AI Interaction Dynamics in Multi-Agent Learning Environments: Supporting Personalised Learning and Reducing Performance Gaps
Multi-agent AI systems, which simulate diverse instructional roles such as teachers and peers, offer new possibilities for personalized and interactive learning. Yet, student-AI interaction patterns and their pedagogical implications remain unclear. This study explores how university students engaged with multiple AI agents, and how these interactions influenced cognitive outcomes (learning gains) and non-cognitive factors (motivation, technology acceptance). Based on MAIC, an online learning p…

It’s Super Bowl or Bust for This Raiders Free Agent Signing https://heavy.com/sports/nfl/las-vegas-raiders/super-bowl-or-bust-free-agent/?adt_ei=[email]

The Automated but Risky Game: Modeling Agent-to-Agent Negotiations and Transactions in Consumer Markets
Shenzhe Zhu, Jiao Sun, Yi Nian, Tobin South, Alex Pentland, Jiaxin Pei
https://arxiv.org/abs/2506.00073

The Automated but Risky Game: Modeling Agent-to-Agent Negotiations and Transactions in Consumer Markets
AI agents are increasingly used in consumer-facing applications to assist with tasks such as product search, negotiation, and transaction execution. In this paper, we explore a future scenario where both consumers and merchants authorize AI agents to fully automate negotiations and transactions. We aim to answer two key questions: (1) Do different LLM agents vary in their ability to secure favorable deals for users? (2) What risks arise from fully automating deal-making with AI agents in consum…

Enterprise vibe coding startup Superblocks raised a $23M Series A, bringing its total funding to $60M, and launched an enterprise coding AI agent called Clark (Julie Bort/TechCrunch)
https://techcrunch.com/2025/06/07/supe…

Superblocks CEO: How to find a unicorn idea by studying AI system prompts | TechCrunch
Brad Menezes, CEO of enterprise vibe coding startup Superblocks, is convinced that the next crop of billion-dollar startup ideas are hiding in almost plain sight: system prompts.

MedChat: A Multi-Agent Framework for Multimodal Diagnosis with Large Language Models
Philip Liu, Sparsh Bansal, Jimmy Dinh, Aditya Pawar, Ramani Satishkumar, Shail Desai, Neeraj Gupta, Xin Wang, Shu Hu
https://arxiv.org/abs/2506.07400

MedChat: A Multi-Agent Framework for Multimodal Diagnosis with Large Language Models
The integration of deep learning-based glaucoma detection with large language models (LLMs) presents an automated strategy to mitigate ophthalmologist shortages and improve clinical reporting efficiency. However, applying general LLMs to medical imaging remains challenging due to hallucinations, limited interpretability, and insufficient domain-specific medical knowledge, which can potentially reduce clinical accuracy. Although recent approaches combining imaging models with LLM reasoning have …

This https://arxiv.org/abs/2504.15585 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across various applications. As LLMs continue to gain prominence in both research and commercial domains, their security and safety implications have become a growing concern, not only for researchers and corporations but also for every nation. Currently, existing surveys…

Jonnu Smith's agent says Dolphins Pro Bowl tight end 'would definitely like to stay in Miami'

https://www.cbssports.com/nfl/news/jonnu-s

Ensemble-MIX: Enhancing Sample Efficiency in Multi-Agent RL Using Ensemble Methods
Tom Danino, Nahum Shimkin
https://arxiv.org/abs/2506.02841 https://

Ensemble-MIX: Enhancing Sample Efficiency in Multi-Agent RL Using Ensemble Methods
Multi-agent reinforcement learning (MARL) methods have achieved state-of-the-art results on a range of multi-agent tasks. Yet, MARL algorithms typically require significantly more environment interactions than their single-agent counterparts to converge, a problem exacerbated by the difficulty in exploring over a large joint action space and the high variance intrinsic to MARL environments. To tackle these issues, we propose a novel algorithm that combines a decomposed centralized critic with d…

IntenTest: Stress Testing for Intent Integrity in API-Calling LLM Agents
Shiwei Feng, Xiangzhe Xu, Xuan Chen, Kaiyuan Zhang, Syed Yusuf Ahmed, Zian Su, Mingwei Zheng, Xiangyu Zhang
https://arxiv.org/abs/2506.07524

IntenTest: Stress Testing for Intent Integrity in API-Calling LLM Agents
LLM agents are increasingly deployed to automate real-world tasks by invoking APIs through natural language instructions. While powerful, they often suffer from misinterpretation of user intent, leading to the agent's actions that diverge from the user's intended goal, especially as external toolkits evolve. Traditional software testing assumes structured inputs and thus falls short in handling the ambiguity of natural language. We introduce IntenTest, an API-centric stress testing framework th…

This https://arxiv.org/abs/2309.14792 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Exploiting Local Observations for Robust Robot Learning
While many robotic tasks can be addressed through either centralized single-agent control with full state observation or decentralized multi-agent control, clear criteria for selecting the optimal approach are lacking. This paper presents a comprehensive investigation into how multi-agent reinforcement learning (MARL) with local observations can enhance robustness in complex robotic systems compared to traditional centralized control methods. We provide both theoretical analysis and empirical v…

Cowboys Urged to Use ‘Brilliant’ Salary Cap Move on $70 Million NFL All-Pro https://heavy.com/sports/nfl/dallas-cowboys/free-agent-free-safety-justin-simmons/?adt_ei=[email]

Inter(sectional) Alia(s): Ambiguity in Voice Agent Identity via Intersectional Japanese Self-Referents
Takao Fujii, Katie Seaborn, Madeleine Steeds, Jun Kato
https://arxiv.org/abs/2506.01998

Inter(sectional) Alia(s): Ambiguity in Voice Agent Identity via Intersectional Japanese Self-Referents
Conversational agents that mimic people have raised questions about the ethics of anthropomorphizing machines with human social identity cues. Critics have also questioned assumptions of identity neutrality in humanlike agents. Recent work has revealed that intersectional Japanese pronouns can elicit complex and sometimes evasive impressions of agent identity. Yet, the role of other "neutral" non-pronominal self-referents (NPSR) and voice as a socially expressive medium remains unexplored. In a…

This https://arxiv.org/abs/2503.02189 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csMA_…

Adaptive Traffic Signal Control based on Multi-Agent Reinforcement Learning. Case Study on a simulated real-world corridor
Previous studies that have formulated multi-agent reinforcement learning (RL) algorithms for adaptive traffic signal control have primarily used value-based RL methods. However, recent literature has shown that policy-based methods may perform better in partially observable environments. Additionally, RL methods remain largely untested for real-world normally signal timing plans because of the simplifying assumptions common in the literature. The current study attempts to address these gaps and…

ATAG: AI-Agent Application Threat Assessment with Attack Graphs
Parth Atulbhai Gandhi, Akansha Shukla, David Tayouri, Beni Ifland, Yuval Elovici, Rami Puzis, Asaf Shabtai
https://arxiv.org/abs/2506.02859

ATAG: AI-Agent Application Threat Assessment with Attack Graphs
Evaluating the security of multi-agent systems (MASs) powered by large language models (LLMs) is challenging, primarily because of the systems' complex internal dynamics and the evolving nature of LLM vulnerabilities. Traditional attack graph (AG) methods often lack the specific capabilities to model attacks on LLMs. This paper introduces AI-agent application Threat assessment with Attack Graphs (ATAG), a novel framework designed to systematically analyze the security risks associated with AI-a…

With Aaron Rodgers, the Steelers risk doing exactly what they said they wouldn't https://www.nytimes.com/athletic/6221842/2025/06/05/aaron-rodgers-steelers-free-agent-signing/

Bills $21 million free agent starter predicted to sign with Raiders https://www.sportingnews.com/us/nfl/las-vegas-raiders/news/bills-21-million-free-agent-starter-predicted-sign-raiders/c321a5…

Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning
Yuheng Lei, Sitong Mao, Shunbo Zhou, Hongyuan Zhang, Xuelong Li, Ping Luo
https://arxiv.org/abs/2506.05985

Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning
A generalist agent must continuously learn and adapt throughout its lifetime, achieving efficient forward transfer while minimizing catastrophic forgetting. Previous work within the dominant pretrain-then-finetune paradigm has explored parameter-efficient fine-tuning for single-task adaptation, effectively steering a frozen pretrained model with a small number of parameters. However, in the context of lifelong learning, these methods rely on the impractical assumption of a test-time task identi…

Generate Realistic Test Scenes for V2X Communication Systems
An Guo, Xinyu Gao, Chunrong Fang, Haoxiang Tian, Weisong Sun, Yanzhou Mu, Shuncheng Tang, Lei Ma, Zhenyu Chen
https://arxiv.org/abs/2506.07419

Generate Realistic Test Scenes for V2X Communication Systems
Accurately perceiving complex driving environments is essential for ensuring the safe operation of autonomous vehicles. With the tremendous progress in deep learning and communication technologies, cooperative perception with Vehicle-to-Everything (V2X) technologies has emerged as a solution to overcome the limitations of single-agent perception systems in perceiving distant objects and occlusions. Despite the considerable advancements, V2X cooperative perception systems require thorough testin…

This https://arxiv.org/abs/2504.19487 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csMA_…

Evolution of Cooperation in LLM-Agent Societies: A Preliminary Study Using Different Punishment Strategies
The evolution of cooperation has been extensively studied using abstract mathematical models and simulations. Recent advances in Large Language Models (LLM) and the rise of LLM agents have demonstrated their ability to perform social reasoning, thus providing an opportunity to test the emergence of norms in more realistic agent-based simulations with human-like reasoning using natural language. In this research, we investigate whether the cooperation dynamics presented in Boyd and Richerson's m…

LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation
Guobin Zhu, Rui Zhou, Wenkang Ji, Shiyu Zhao
https://arxiv.org/abs/2506.01538

LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation
Although Multi-Agent Reinforcement Learning (MARL) is effective for complex multi-robot tasks, it suffers from low sample efficiency and requires iterative manual reward tuning. Large Language Models (LLMs) have shown promise in single-robot settings, but their application in multi-robot systems remains largely unexplored. This paper introduces a novel LLM-Aided MARL (LAMARL) approach, which integrates MARL with LLMs, significantly enhancing sample efficiency without requiring manual design. LA…

Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents
Yun Hua, Haosheng Chen, Shiqin Wang, Wenhao Li, Xiangfeng Wang, Jun Luo
https://arxiv.org/abs/2506.07388

Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents
Large Language Models (LLMs) show strong collaborative performance in multi-agent systems with predefined roles and workflows. However, in open-ended environments lacking coordination rules, agents tend to act in self-interested ways. The central challenge in achieving coordination lies in credit assignment -- fairly evaluating each agent's contribution and designing pricing mechanisms that align their heterogeneous goals. This problem is critical as LLMs increasingly participate in complex hum…

Investigation into fatal golf cart incident involving John Elway's former agent to remain open

https://www.cbssports.com/nfl/news/investi

Attention Knows Whom to Trust: Attention-based Trust Management for LLM Multi-Agent Systems
Pengfei He, Zhenwei Dai, Xianfeng Tang, Yue Xing, Hui Liu, Jingying Zeng, Qiankun Peng, Shrivats Agrawal, Samarth Varshney, Suhang Wang, Jiliang Tang, Qi He
https://arxiv.org/abs/2506.02546

Attention Knows Whom to Trust: Attention-based Trust Management for LLM Multi-Agent Systems
Large Language Model-based Multi-Agent Systems (LLM-MAS) have demonstrated strong capabilities in solving complex tasks but remain vulnerable when agents receive unreliable messages. This vulnerability stems from a fundamental gap: LLM agents treat all incoming messages equally without evaluating their trustworthiness. While some existing studies approach the trustworthiness, they focus on a single type of harmfulness rather than analyze it in a holistic approach from multiple trustworthiness p…

HASHIRU: Hierarchical Agent System for Hybrid Intelligent Resource Utilization
Kunal Pai, Parth Shah, Harshil Patel
https://arxiv.org/abs/2506.04255 https:…

HASHIRU: Hierarchical Agent System for Hybrid Intelligent Resource Utilization
Rapid Large Language Model (LLM) advancements are fueling autonomous Multi-Agent System (MAS) development. However, current frameworks often lack flexibility, resource awareness, model diversity, and autonomous tool creation. This paper introduces HASHIRU (Hierarchical Agent System for Hybrid Intelligent Resource Utilization), a novel MAS framework enhancing flexibility, resource efficiency, and adaptability. HASHIRU features a "CEO" agent dynamically managing specialized "employee" agents, ins…

Vikings' Kevin O'Connell details previous talks with Aaron Rodgers after Steelers sign four-time NFL MVP

https://www.cbssports.com/nfl/news…

Next Woman Up: Faith Lee, Player Personnel Coordinator for the Arizona Cardinals https://www.nfl.com/news/next-woman-up-faith-lee-player-personnel-coordinator-for-the-arizona-cardinals

Literature Review Of Multi-Agent Debate For Problem-Solving
Arne Tillmann
https://arxiv.org/abs/2506.00066 https://arxiv.org/pdf/2506…

Literature Review Of Multi-Agent Debate For Problem-Solving
Multi-agent large language models (MA-LLMs) are a rapidly growing research area that leverages multiple interacting language agents to tackle complex tasks, outperforming single-agent large language models. This literature review synthesizes the latest research on agent profiles, communication structures, and decision-making processes, drawing insights from both traditional multi-agent systems and state-of-the-art MA-LLM studies. In doing so, it aims to address the lack of direct comparisons in…

CORA: Coalitional Rational Advantage Decomposition for Multi-Agent Policy Gradients
Mengda Ji, Genjiu Xu, Liying Wang
https://arxiv.org/abs/2506.04265 http…

CORA: Coalitional Rational Advantage Decomposition for Multi-Agent Policy Gradients
This work focuses on the credit assignment problem in cooperative multi-agent reinforcement learning (MARL). Sharing the global advantage among agents often leads to suboptimal policy updates as it fails to account for the distinct contributions of agents. Although numerous methods consider global or individual contributions for credit assignment, a detailed analysis at the coalition level remains lacking in many approaches. This work analyzes the over-updating problem during multi-agent policy…

This https://arxiv.org/abs/2505.00212 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csMA_…

Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
Failure attribution in LLM multi-agent systems-identifying the agent and step responsible for task failures-provides crucial clues for systems debugging but remains underexplored and labor-intensive. In this paper, we propose and formulate a new research area: automated failure attribution for LLM multi-agent systems. To support this initiative, we introduce the Who&When dataset, comprising extensive failure logs from 127 LLM multi-agent systems with fine-grained annotations linking failures to…

Modeling human reputation-seeking behavior in a spatio-temporally complex public good provision game
Edward Hughes, Tina O. Zhu, Martin J. Chadwick, Raphael Koster, Antonio Garc\'ia Casta\~neda, Charles Beattie, Thore Graepel, Matthew M. Botvinick, Joel Z. Leibo
https://arxiv.org/abs/2506.06032…

Modeling human reputation-seeking behavior in a spatio-temporally complex public good provision game
Multi-agent reinforcement learning algorithms are useful for simulating social behavior in settings that are too complex for other theoretical approaches like game theory. However, they have not yet been empirically supported by laboratory experiments with real human participants. In this work we demonstrate how multi-agent reinforcement learning can model group behavior in a spatially and temporally complex public good provision game called Clean Up. We show that human groups succeed in Clean …