Tootfinder

Towards Data-Driven Model-Free Safety-Critical Control
Zhe Shen, Yitaek Kim, Christoffer Sloth
https://arxiv.org/abs/2506.06931 https://

Towards Data-Driven Model-Free Safety-Critical Control
This paper presents a framework for enabling safe velocity control of general robotic systems using data-driven model-free Control Barrier Functions (CBFs). Model-free CBFs rely on an exponentially stable velocity controller and a design parameter (e.g. alpha in CBFs); this design parameter depends on the exponential decay rate of the controller. However, in practice, the decay rate is often unavailable, making it non-trivial to use model-free CBFs, as it requires manual tuning for alpha. To ad…

This https://arxiv.org/abs/2501.00296 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models
Our aim is to learn to solve long-horizon decision-making problems in complex robotics domains given low-level skills and a handful of short-horizon demonstrations containing sequences of images. To this end, we focus on learning abstract symbolic world models that facilitate zero-shot generalization to novel goals via planning. A critical component of such models is the set of symbolic predicates that define properties of and relationships between objects. In this work, we leverage pretrained …

This https://arxiv.org/abs/2505.24492 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Object Centric Concept Bottlenecks
Developing high-performing, yet interpretable models remains a critical challenge in modern AI. Concept-based models (CBMs) attempt to address this by extracting human-understandable concepts from a global encoding (e.g., image encoding) and then applying a linear classifier on the resulting concept activations, enabling transparent decision-making. However, their reliance on holistic image encodings limits their expressiveness in object-centric real-world settings and thus hinders their abilit…

Critical demand in a stochastic model of flows in supply networks
Yannick Feld, Marc Barthelemy
https://arxiv.org/abs/2505.24813 https://

Critical demand in a stochastic model of flows in supply networks
Supply networks are essential for modern production, yet their critical properties remain understudied. We present a stochastic model with random production capacities to analyze material flow to a root node, focusing on topology and buffer stocks. The critical demand, where unsatisfied demand diverges, is examined mostly through numerical simulations. Without stocks, minimal production dictates behavior, making topology irrelevant. With stocks, memory effects arise, making topology crucial. In…

This https://arxiv.org/abs/2411.07161 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csMA_…

RoundTable: Investigating Group Decision-Making Mechanism in Multi-Agent Collaboration
Effective group decision-making is critical in Multi-Agent Systems (MAS). Yet, how different mechanisms for reaching consensus impact collaboration quality and efficiency remains understudied. We conduct a systematic study on group decision-making mechanisms in a decentralized setting. Through controlled experiments, we analyze how different voting rules affect decision quality and efficiency in a multi-round collaboration. Results reveal that majority voting often cause inefficient collaborati…

This https://arxiv.org/abs/2409.08665 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Agile Decision-Making and Safety-Critical Motion Planning for Emergency Autonomous Vehicles
Efficiency is critical for autonomous vehicles (AVs), especially for emergency AVs. However, most existing methods focus on regular vehicles, overlooking the distinct strategies required by emergency vehicles to address the challenge of maximizing efficiency while ensuring safety. In this paper, we propose an Integrated Agile Decision-Making with Active and Safety-Critical Motion Planning System (IDEAM). IDEAM focuses on enabling emergency AVs, such as ambulances, to actively attain efficiency …

This https://arxiv.org/abs/2505.23667 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Fortune: Formula-Driven Reinforcement Learning for Symbolic Table Reasoning in Language Models
Tables are a fundamental structure for organizing and analyzing data, making effective table understanding a critical capability for intelligent systems. While large language models (LMs) demonstrate strong general reasoning abilities, they continue to struggle with accurate numerical or symbolic reasoning over tabular data, especially in complex scenarios. Spreadsheet formulas provide a powerful and expressive medium for representing executable symbolic operations, encoding rich reasoning patt…

This https://arxiv.org/abs/2505.22906 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

HiLDe: Intentional Code Generation via Human-in-the-Loop Decoding
While AI programming tools hold the promise of increasing programmers' capabilities and productivity to a remarkable degree, they often exclude users from essential decision-making processes, causing many to effectively "turn off their brains" and over-rely on solutions provided by these systems. These behaviors can have severe consequences in critical domains, like software security. We propose Human-in-the-loop Decoding, a novel interaction technique that allows users to observe and directly …

Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values
John P. Dickerson, Hadi Hosseini, Samarth Khanna, Leona Pierce
https://arxiv.org/abs/2506.00079

Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values
The rapid integration of Large Language Models (LLMs) in high-stakes decision-making -- such as allocating scarce resources like donor organs -- raises critical questions about their alignment with human moral values. We systematically evaluate the behavior of several prominent LLMs against human preferences in kidney allocation scenarios and show that LLMs: i) exhibit stark deviations from human values in prioritizing various attributes, and ii) in contrast to humans, LLMs rarely express indec…

This https://arxiv.org/abs/2310.00468 has been replaced.
link: https://scholar.google.com/scholar?q=a

When Should a Leader Act Suboptimally? The Role of Inferability in Repeated Stackelberg Games
When interacting with other decision-making agents in non-adversarial scenarios, it is critical for an autonomous agent to have inferable behavior: The agent's actions must convey their intention and strategy. We model the inferability problem using Stackelberg games with observations where a leader and a follower repeatedly interact. During the interactions, the leader uses a fixed mixed strategy. The follower does not know the leader's strategy and dynamically reacts to the statistically infe…

Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion
Chunlong Xie, Jialing He, Shangwei Guo, Jiacheng Wang, Shudong Zhang, Tianwei Zhang, Tao Xiang
https://arxiv.org/abs/2505.23266

Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion
We present Adversarial Object Fusion (AdvOF), a novel attack framework targeting vision-and-language navigation (VLN) agents in service-oriented environments by generating adversarial 3D objects. While foundational models like Large Language Models (LLMs) and Vision Language Models (VLMs) have enhanced service-oriented navigation systems through improved perception and decision-making, their integration introduces vulnerabilities in mission-critical service workflows. Existing adversarial attac…

This https://arxiv.org/abs/2403.12093 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_eco…

Learning Macroeconomic Policies through Dynamic Stackelberg Mean-Field Games
Macroeconomic outcomes emerge from individuals' decisions, making it essential to model how agents interact with macro policy via consumption, investment, and labor choices. We formulate this as a dynamic Stackelberg game: the government (leader) sets policies, and agents (followers) respond by optimizing their behavior over time. Unlike static models, this dynamic formulation captures temporal dependencies and strategic feedback critical to policy design. However, as the number of agents incre…

BASIL: Best-Action Symbolic Interpretable Learning for Evolving Compact RL Policies
Kourosh Shahnazari, Seyed Moein Ayyoubzadeh, Mohammadali Keshtparvar
https://arxiv.org/abs/2506.00328

BASIL: Best-Action Symbolic Interpretable Learning for Evolving Compact RL Policies
The quest for interpretable reinforcement learning is a grand challenge for the deployment of autonomous decision-making systems in safety-critical applications. Modern deep reinforcement learning approaches, while powerful, tend to produce opaque policies that compromise verification, reduce transparency, and impede human oversight. To address this, we introduce BASIL (Best-Action Symbolic Interpretable Learning), a systematic approach for generating symbolic, rule-based policies via online ev…

Large language models can learn and generalize steganographic chain-of-thought under process supervision
Joey Skaf, Luis Ibanez-Lissen, Robert McCarthy, Connor Watts, Vasil Georgiv, Hannes Whittingham, Lorena Gonzalez-Manzano, David Lindner, Cameron Tice, Edward James Young, Puria Radmard
https://arxiv.org/abs/2506.01926

Large language models can learn and generalize steganographic chain-of-thought under process supervision
Chain-of-thought (CoT) reasoning not only enhances large language model performance but also provides critical insights into decision-making processes, marking it as a useful tool for monitoring model intent and planning. By proactively preventing models from acting on CoT indicating misaligned or harmful intent, CoT monitoring can be used to reduce risks associated with deploying models. However, developers may be incentivized to train away the appearance of harmful intent from CoT traces, by …

Towards Efficient Key-Value Cache Management for Prefix Prefilling in LLM Inference
Yue Zhu, Hao Yu, Chen Wang, Zhuoran Liu, Eun Kyung Lee
https://arxiv.org/abs/2505.21919

Towards Efficient Key-Value Cache Management for Prefix Prefilling in LLM Inference
The increasing adoption of large language models (LLMs) with extended context windows necessitates efficient Key-Value Cache (KVC) management to optimize inference performance. Inference workloads like Retrieval-Augmented Generation (RAG) and agents exhibit high cache reusability, making efficient caching critical to reducing redundancy and improving speed. We analyze real-world KVC access patterns using publicly available traces and evaluate commercial key-value stores like Redis and state-of-…

Stationary and Non-Stationary Transition Probabilities in Decision Making: Modeling COVID-19 Dynamics
Romario Gildas Foko Tiomela, Serges Love Teutu Talla, Samson Adekola Alagbe, Olawale Nasiru Lawal, Isabella Kemajou-Brown
https://arxiv.org/abs/2505.21519

Stationary and Non-Stationary Transition Probabilities in Decision Making: Modeling COVID-19 Dynamics
This study explores the complexities of stationary and non-stationary transition probabilities within the framework of a Markov Decision Process (MDP), specifically applied to COVID-19. The research highlights the critical role these probabilities play in accurately modeling disease dynamics and informing evidence-based decisions by policymakers and public health authorities. By incorporating both stationary transition probabilities (which assume constant rates of state changes) and non-station…

World Models for Cognitive Agents: Transforming Edge Intelligence in Future Networks
Changyuan Zhao, Ruichen Zhang, Jiacheng Wang, Gaosheng Zhao, Dusit Niyato, Geng Sun, Shiwen Mao, Dong In Kim
https://arxiv.org/abs/2506.00417

World Models for Cognitive Agents: Transforming Edge Intelligence in Future Networks
World models are emerging as a transformative paradigm in artificial intelligence, enabling agents to construct internal representations of their environments for predictive reasoning, planning, and decision-making. By learning latent dynamics, world models provide a sample-efficient framework that is especially valuable in data-constrained or safety-critical scenarios. In this paper, we present a comprehensive overview of world models, highlighting their architecture, training paradigms, and a…

The Stablecoin Discount: Evidence of Tether's U.S. Treasury Bill Market Share in Lowering Yields
Lennart Ante, Aman Saggu, Ingo Fiedler
https://arxiv.org/abs/2505.12413

The Stablecoin Discount: Evidence of Tether's U.S. Treasury Bill Market Share in Lowering Yields
Stablecoins represent a critical bridge between cryptocurrency and traditional finance, with Tether (USDT) dominating the sector as the largest stablecoin by market capitalization. By Q1 2025, Tether directly held approximately $98.5 billion in U.S. Treasury bills, representing 1.6% of all outstanding Treasury bills, making it one of the largest non-sovereign buyers in this crucial asset class, on par with nation-state-level investors. This paper investigates how Tether's market share of U.S. T…