Tootfinder

Sorry, heute wenigstens bis jetzt einen Lauf.
#pastpuzzle 373
🟩🟩🟩🟩 (0)
▪️▪️▪️▪️
▪️▪️▪️▪️
▪️▪️▪️▪️
1/4 🥇
https://www.pastpuzzle.de

No, it's not DNS! It can't be!

Ripple Effects
Hosted by Soph Dicker from So Invested following Australian founders and VC operators on a transformative two-week journey in Tanzania...
Great Australian Pods Podcast Directory: https://www.greataustralianpods.com/ripple-effects/

Irgendwie hatte ich für einen Kurzurlaub auch schon weniger Gepäck. 🤨🤷‍♂️
Könnte an Jahreszeit und Destination liegen. Genügend warme Klamotten und Schuhe waren das Ziel, also einen Jacken-/Schuhkoffer mitgenommen.
#CANEast25

Bret Taylor says his AI agent startup Sierra has hit $100M in ARR, after launching in February 2024, up from about $20M this time last year (Alex Heath/Sources)
https://sources.news/p/sierras-revenue-flex

Sierra's revenue flex
ARR is the new AI startup recruiting pitch. Also: Harvey's Winston Weinberg this week on ACCESS.

Home Assistant really puts the ass in assistant
However, I've got my Sekki card and sensor working at last (h/t @…)

»Rechenzentren — Ökostrom deutlich günstiger als Atomkraft:
KI-Modelle benötigten Rechenzentren mit einem gigantischen Strombedarf. Um diesen zu decken, setzen viele Unternehmen auf Atomkraft. Doch erneuerbare Energien sind offenbar deutlich günstiger und effektiver.«
Weshalb kann man Menschen des öfteren anhand von Finanzfakten überzeugen und fast nicht mit positiven Argumente für die Allgemeingesellschaft & Umweltschutz?
🔌

Rechenzentren: Ökostrom deutlich günstiger als Atomkraft
Um den Strombedarf von KI-Rechenzentren zu decken, setzen viele Firmen auf Atomkraft. Doch erneuerbare Energien sind deutlich günstiger.

i was jamming this solo guitar LP by liam grant last year when my turntable troubles began. the wobble hit during a slow spare loren connors cover so i thought it was intentional 'til i changed records. l'il traumatizing & haven't listened since, but way hip! https://vhfrecords.bandcamp.com/album/

XMPP is here. Don't forget about it.
#xmpp

It's frustrating when using `leaks` to examine a leaking process, and it causes `leaks` to leak harder than the originally-leaking process did...

🌪️ The housing crisis is forcing Americans to choose between affordability and safety
https://theconversation.com/the-housing-crisis-is-forcing-americans-to-choose-between-affordability-and-safety-266136
<…

The housing crisis is forcing Americans to choose between affordability and safety
Priced out of ‘safe,’ more and more Americans are moving to flood plains and fire zones.

This month, GÉANT was in Ireland for HEAnet Conference 2025!
Our CEO Lise Fuhr joined the panel with Ronan Byrne (HEAnet), Heidi Fraser-Krauss (Jisc), and Dr Gerard Culley (University College Cork).
And our very own Monique Pellinkhof & Magdalena Rząca also joined the programme, unpacking the future of EU collaborations, and what the EU AI Act means for the R&E community.
👏 A big thank you to the HEAnet team for an excellent event!

As much as Quebec goes too far with laïcité, especially around dictating what you can wear and prayers in public space.
The other side with Ontario can also be absolutely bonkers.
My city councillor spreading her Christian faith in her newsletter and organizing a praying group within city hall, it’s absolutely not the place
#topoli

Skål #drinkklubben!

Bitte nochmal alle aufpassen, die das gute alte Internet verpasst oder vergessen haben: Ein #Podcast zeichnet sich *nicht* dadurch aus, dass er „leider nur auf #Spotify veröffentlicht“ ist.
Insbesondere nicht, wenn Ihr darin über

Ich habe im Laufe der Zeit immer mal wieder Personen und Gruppen zum Thema #Mastodon bzw. #Fediverse Einstieg beraten. Heute habe ich mal die aus meiner Sicht wichtigsten Tipps zusammengeschrieben:

Küchenmaschine defekt. Ohne dass sie läuft, britzelt es und macht Puff. Sicherung fliegt raus.
Die Bosch MUM ist sicher 20 Jahre alt und läuft täglich. Aber ich mag es nicht, Dinge wegzuwerfen und zudem haben wir zahlreiches Zubehör, bishin zur Steinmühle.
Also aufgeschraubt, Fehlersuche.
Da der Motor nicht lief, muß das Problem in der Zuleitung stecken. Das Kabel ausgebaut, aber kein Kurzschluss zu erkennen.
und - sind mit Steckern an der Platine befestigt. Also aufs…

Der #RepairThursday ist nun auch Teil der europäischen Woche der Abfallvermeidung #EWAV2025
https://letsc…

https://defend612.com has been blocked at the domain name level for me and at least two other people over T-Mobile networks (which includes GoogleFi, MetroPCS, and… wait for it… Trump Mobile). For at least all day today.
Seems unlikely to be a technical problem but instead to be Actual Censorship (unless its not …

Ein guter Outdoor #Buschhut ist unverzichtbar für #Sonnenschutz und UV-Schutz.
Zusätzlich sollte man auf langen #Wanderungen

Replaced article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- Stop Playing the Guessing Game! Target-free User Simulation for Evaluating Conversational Recomme...
Sunghwan Kim, Tongyoung Kim, Kwangwook Seo, Jinyoung Yeo, Dongha Lee

A US journalist friend mentioned the #artillery incident to me yesterday.
I can’t find anything at all about it in Australian media. Nothing. I’m a little shocked, to say the least. What else are we just not getting?
#Free NYT

Military Fired Artillery Over California Freeway on Saturday
Rounds were fired on Friday across Interstate 5 as part of a test for Saturday’s event in Southern California. The state shut a section of the freeway.

Metrolinx board meeting slideshow mentioned December 7th as opening date for the Finch LRT
#metrolinx

In episode 207 I shared advice from six former podcast guests on what they do to improve or maintain their own mental health. Hear what Jasmine Sleigh says about sleep, and about actually doing the things that helps us rather than just aspiring to do them!

Heged\"{u}s Szil\`agyi Fixed Point Theorem by Hardy Rogers and Interpolative approach
Anuradha Gupta, Rahul Mansotra
https://arxiv.org/abs/2509.15624 https://

Hegedüs Szilàgyi Fixed Point Theorem by Hardy Rogers and Interpolative approach
In this article, three new types (I), (II), (III) of Hegedüs Szilàgyi contraction on metric spaces by interpolative and Hardy-Rogers methods have been introduced. Moreover, we give the fixed point theorems in this setting, along with examples to justify the novelty of these contractions.

Last photos from that day in the #schwarzwald . We were pretty surprised when we came to the part shown in the last photo. The #moss was so thick there - like a real carpet! I've never seen such before. I found it pretty hard to get a photo that pays the situation justice. I hope it works for …

#coffee

aktuelles #Wetter #Behrendorf #Wische 20-12-2025 10:10
Temperatur: (min: 1,7C) 2,9C (max: 8,2C)
Feuchte: 99%
Luftdruck: 1019,7 hPa (gleichbleibend)
Windrichtung: N/A Grad
Wi…

Es gibt also nicht nur ein Cannes, sondern kurz davor auch noch ein Cagnes. Das muss die sonnige Variante des Verwirrspiels von Dietikon/Dietlikon sein. Aber hey, hintergrundbeleuchtete Steckdosen im Zug sind schon fancy (auch wenn sie, wie die Trams hier auch, offensichtlich nicht auf maximal einfachen Passagierfluss ausgelegt sind).
#bahnbubble

Evaluation of LLMs for Process Model Analysis and Optimization
Akhil Kumar, Jianliang Leon Zhao, Om Dobariya
https://arxiv.org/abs/2510.07489 https://arxiv…

Evaluation of LLMs for Process Model Analysis and Optimization
In this paper, we report our experience with several LLMs for their ability to understand a process model in an interactive, conversational style, find syntactical and logical errors in it, and reason with it in depth through a natural language (NL) interface. Our findings show that a vanilla, untrained LLM like ChatGPT (model o3) in a zero-shot setting is effective in understanding BPMN process models from images and answering queries about them intelligently at syntactic, logic, and semantic …

Der #RepairThursday am 27.-29.11.25 steht vor der Tür:
https://www.zuerich.repair/repairthursday2025/
Macht alle mit bei unserem

I’m sure it’s a difficult situation for many but…
I just want to see those confused Waymo in the San Francisco blackout
#sanfrancisco

Crosslisted article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Cluster...
Nan Li, Bo Kang, Tijl De Bie

I've been lucky to run an ecommerce store for 10 years and only got 2 chargebacks.
One of them was a fraudulent one, where customer received the item but claimed it was defective without contacting us, sending us a photo or giving us a chance to make it right. For all we know, it was not defective.
Just won the chargeback dispute, which is actually not too frequent.
#ecommerce

Optimizing Product Deduplication in E-Commerce with Multimodal Embeddings
Aysenur Kulunk, Berk Taskin, M. Furkan Eseoglu, H. Bahadir Sahin
https://arxiv.org/abs/2509.15858 https…

Optimizing Product Deduplication in E-Commerce with Multimodal Embeddings
In large scale e-commerce marketplaces, duplicate product listings frequently cause consumer confusion and operational inefficiencies, degrading trust on the platform and increasing costs. Traditional keyword-based search methodologies falter in accurately identifying duplicates due to their reliance on exact textual matches, neglecting semantic similarities inherent in product titles. To address these challenges, we introduce a scalable, multimodal product deduplication designed specifically f…

There's a tool that analyses your 2025 hackernews comments through a LLM and give you a summary
Who am I:
The Fediverse Urbanist
A supply-and-demand fundamentalist who divides their time equally between defending housing density and explaining why your social media platform is a centralized prison for bots. You have successfully mapped the entire journey from a car-dependent suburb to a Mastodon instance using only RSS feeds and a burning hatred for high-tariff border …

11/16/85 long beach: rare post-’74 2nd set TENNESSEE JED, last time as set opener, more juice than usual; same for CUMBERLAND BLUES, a lesh slot. 57-minute CRAZY FINGERS > DRUMZ > SPACE > COMES A TIME > GIMME SOME LOVIN’ > TRUCKIN’ > BLACK PETER > GOOD LOVIN’. shaky CRAZY FINGERS lyrics, but deep wounded COMES A TIME holds achingly steady. solid Beamin’ melts to thoughtful garcia/weir SPACE. GIMME SOME LOVIN’ vocal jamminess. weir takes mic off stand & wanders for GO…

Ohne die Bemalung würde diese Kurve ja gar niemand kennen.

ExpertAgent: Enhancing Personalized Education through Dynamic Planning and Retrieval-Augmented Long-Chain Reasoning
Binrong Zhu, Guiran Liu, Nina Jiang
https://arxiv.org/abs/2510.07456

ExpertAgent: Enhancing Personalized Education through Dynamic Planning and Retrieval-Augmented Long-Chain Reasoning
The application of advanced generative artificial intelligence in education is often constrained by the lack of real-time adaptability, personalization, and reliability of the content. To address these challenges, we propose ExpertAgent - an intelligent agent framework designed for personalized education that provides reliable knowledge and enables highly adaptive learning experiences. Therefore, we developed ExpertAgent, an innovative learning agent that provides users with a proactive and per…

Beyond Meat seems to be the new meme stock
#beyondmeat #wsb #wallstreetbets

Understanding Embedding Scaling in Collaborative Filtering
Zhuangzhuang He, Zhou Kaiyu, Haoyue Bai, Fengbin Zhu, Yonghui Yang
https://arxiv.org/abs/2509.15709 https://

Understanding Embedding Scaling in Collaborative Filtering
Scaling recommendation models into large recommendation models has become one of the most widely discussed topics. Recent efforts focus on components beyond the scaling embedding dimension, as it is believed that scaling embedding may lead to performance degradation. Although there have been some initial observations on embedding, the root cause of their non-scalability remains unclear. Moreover, whether performance degradation occurs across different types of models and datasets is still an un…

Drop Site uncovered new information about individuals, donor networks, and businesses helping Canary Mission, a pro-Israel organization serving the U.S.'s deportation and repression efforts.
https://www.dropsitenews.com/p/canary-miss

Was man nicht alles lernt, wenn man mit der #Tochter in den #Ferien ist. Man kann im Kleidergeschäft auch Plastiksäcke kaufen. Und sicher gibt es die selben auch zuhause.
#bershka

Chunk Knowledge Generation Model for Enhanced Information Retrieval: A Multi-task Learning Approach
Jisu Kim, Jinhee Park, Changhyun Jeon, Jungwoo Choi, Keonwoo Kim, Minji Hong, Sehyun Kim
https://arxiv.org/abs/2509.15658

Chunk Knowledge Generation Model for Enhanced Information Retrieval: A Multi-task Learning Approach
Traditional query expansion techniques for addressing vocabulary mismatch problems in information retrieval are context-sensitive and may lead to performance degradation. As an alternative, document expansion research has gained attention, but existing methods such as Doc2Query have limitations including excessive preprocessing costs, increased index size, and reliability issues with generated content. To mitigate these problems and seek more structured and efficient alternatives, this study pr…

TS-Agent: A Time Series Reasoning Agent with Iterative Statistical Insight Gathering
Penghang Liu, Elizabeth Fons, Svitlana Vyetrenko, Daniel Borrajo, Vamsi Potluru, Manuela Veloso
https://arxiv.org/abs/2510.07432

TS-Agent: A Time Series Reasoning Agent with Iterative Statistical Insight Gathering
Large language models (LLMs) have shown strong abilities in reasoning and problem solving, but recent studies reveal that they still struggle with time series reasoning tasks, where outputs are often affected by hallucination or knowledge leakage. In this work we propose TS-Agent, a time series reasoning agent that leverages LLMs strictly for what they excel at, i.e., gathering evidence and synthesizing it into conclusions through step-by-step reasoning, while delegating the extraction of stati…

If anyone is interested in decentralized web in #Toronto there's a group starting to have monthly meetups/presentations, starting in January #dweb

Take it from a suburban GTA driver: Doug Ford’s toll-free Highway 407 is just not working
What a surprise, removing the tolls on the 407 East increased traffic and now it's no longer the shortcut it was.
https://www.

CFDA & CLIP at TREC iKAT 2025: Enhancing Personalized Conversational Search via Query Reformulation and Rank Fusion
Yu-Cheng Chang, Guan-Wei Yeo, Quah Eugene, Fan-Jie Shih, Yuan-Ching Kuo, Tsung-En Yu, Hung-Chun Hsu, Ming-Feng Tsai, Chuan-Ju Wang
https://arxiv.org/abs/2509.15588

CFDA & CLIP at TREC iKAT 2025: Enhancing Personalized Conversational Search via Query Reformulation and Rank Fusion
The 2025 TREC Interactive Knowledge Assistance Track (iKAT) featured both interactive and offline submission tasks. The former requires systems to operate under real-time constraints, making robustness and efficiency as important as accuracy, while the latter enables controlled evaluation of passage ranking and response generation with pre-defined datasets. To address this, we explored query rewriting and retrieval fusion as core strategies. We built our pipelines around Best-of-$N$ selection a…

Die Tochter hat den Hairstraightener und ihren eigenen Fön ausgepackt. Was man so alles braucht für eine Reise an die Côte d‘Azur. Aber sie buckelt das Zeugs selbst vom Bahnhof zum Hotel.

Seems like downtown #Toronto was/is busy with Blue Jays celebration?
Saw this screenshot on Facebook

Less is More: Strategic Expert Selection Outperforms Ensemble Complexity in Traffic Forecasting
Walid Guettala, Yufan Zhao, L\'aszl\'o Guly\'as
https://arxiv.org/abs/2510.07426

Less is More: Strategic Expert Selection Outperforms Ensemble Complexity in Traffic Forecasting
Traffic forecasting is fundamental to intelligent transportation systems, enabling congestion mitigation and emission reduction in increasingly complex urban environments. While recent graph neural network approaches have advanced spatial temporal modeling, existing mixture of experts frameworks like Time Enhanced Spatio Temporal Attention Model (TESTAM) lack explicit incorporation of physical road network topology, limiting their spatial capabilities. We present TESTAM+, an enhanced spatio tem…

Dual-Mode Visual System for Brain-Computer Interfaces: Integrating SSVEP and P300 Responses
Ekgari Kasawala, Surej Mouli
https://arxiv.org/abs/2509.15439 https://

Dual-Mode Visual System for Brain-Computer Interfaces: Integrating SSVEP and P300 Responses
In brain-computer interface (BCI) systems, steady-state visual evoked potentials (SSVEP) and P300 responses have achieved widespread implementation owing to their superior information transfer rates (ITR) and minimal training requirements. These neurophysiological signals have exhibited robust efficacy and versatility in external device control, demonstrating enhanced precision and scalability. However, conventional implementations predominantly utilise liquid crystal display (LCD)-based visual…

Cette campagne municipale de Sam Hamad est un vrai délice
#villedequebec

SERVAL: Surprisingly Effective Zero-Shot Visual Document Retrieval Powered by Large Vision and Language Models
Thong Nguyen, Yibin Lei, Jia-Huei Ju, Andrew Yates
https://arxiv.org/abs/2509.15432

SERVAL: Surprisingly Effective Zero-Shot Visual Document Retrieval Powered by Large Vision and Language Models
Visual Document Retrieval (VDR) typically operates as text-to-image retrieval using specialized bi-encoders trained to directly embed document images. We revisit a zero-shot generate-and-encode pipeline: a vision-language model first produces a detailed textual description of each document image, which is then embedded by a standard text encoder. On the ViDoRe-v2 benchmark, the method reaches 63.4% nDCG@5, surpassing the strongest specialised multi-vector visual document encoder. It also scales…

Etwas Badezimmercontent.
(Jetzt bin ich gespannt, was der altbot aus dem #Bidet macht).
#hotel #badezimmer

ProSEA: Problem Solving via Exploration Agents
William Nguyen, Vinh Luong, Christopher Nguyen
https://arxiv.org/abs/2510.07423 https://arxiv.org/pdf/2510.0…

ProSEA: Problem Solving via Exploration Agents
Large language models (LLMs) have empowered AI agents to tackle increasingly complex tasks. However, most existing agents remain limited to static planning and brittle interactions, falling short of true collaboration or adaptive reasoning. We introduce ProSEA, a modular, general-purpose multi-agent framework designed for iterative problem solving through exploration and plan evolution. ProSEA features a hierarchical architecture in which a Manager Agent orchestrates domain-specialized Expert A…

Efficient and Versatile Model for Multilingual Information Retrieval of Islamic Text: Development and Deployment in Real-World Scenarios
Vera Pavlova, Mohammed Makhlouf
https://arxiv.org/abs/2509.15380

Efficient and Versatile Model for Multilingual Information Retrieval of Islamic Text: Development and Deployment in Real-World Scenarios
Despite recent advancements in Multilingual Information Retrieval (MLIR), a significant gap remains between research and practical deployment. Many studies assess MLIR performance in isolated settings, limiting their applicability to real-world scenarios. In this work, we leverage the unique characteristics of the Quranic multilingual corpus to examine the optimal strategies to develop an ad-hoc IR system for the Islamic domain that is designed to satisfy users' information needs in multiple la…

[2025-09-22 Mon (UTC), 7 new articles found for cs.IR Information Retrieval]
toXiv_bot_toot

Position: AI Will Transform Neuropsychology Through Mental Health Digital Twins for Dynamic Mental Health Care, Especially for ADHD
Neil Natarajan, Sruthi Viswanathan, Xavier Roberts-Gaal, Michelle Marie Martel
https://arxiv.org/abs/2510.07409

Position: AI Will Transform Neuropsychology Through Mental Health Digital Twins for Dynamic Mental Health Care, Especially for ADHD
Static solutions don't serve a dynamic mind. Thus, we advocate a shift from static mental health diagnostic assessments to continuous, artificial intelligence (AI)-driven assessment. Focusing on Attention-Deficit/Hyperactivity Disorder (ADHD) as a case study, we explore how generative AI has the potential to address current capacity constraints in neuropsychology, potentially enabling more personalized and longitudinal care pathways. In particular, AI can efficiently conduct frequent, low-level…

#pastpuzzle 146
🟩🟨🟨🟩 (-90)
🟩🟩🟩🟩 (0)
▪️▪️▪️▪️
▪️▪️▪️▪️
2/4 🥈
https://www.pastpuzzle.de

Base Models Know How to Reason, Thinking Models Learn When
Constantin Venhoff, Iv\'an Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda
https://arxiv.org/abs/2510.07364 https…

Base Models Know How to Reason, Thinking Models Learn When
Why do thinking language models like DeepSeek R1 outperform their base counterparts? Despite consistent performance gains, it remains unclear to what extent thinking models learn entirely new reasoning capabilities or repurpose pre-existing base model ones. In this work, we propose a hybrid model where we activate reasoning mechanisms in base models at the right time to elicit thinking-model-level reasoning chains, implying that thinking models exploit already existing capabilities. To ground o…

L2M-AID: Autonomous Cyber-Physical Defense by Fusing Semantic Reasoning of Large Language Models with Multi-Agent Reinforcement Learning (Preprint)
Tianxiang Xu, Zhichao Wen, Xinyu Zhao, Jun Wang, Yan Li, Chang Liu
https://arxiv.org/abs/2510.07363

L2M-AID: Autonomous Cyber-Physical Defense by Fusing Semantic Reasoning of Large Language Models with Multi-Agent Reinforcement Learning (Preprint)
The increasing integration of Industrial IoT (IIoT) exposes critical cyber-physical systems to sophisticated, multi-stage attacks that elude traditional defenses lacking contextual awareness. This paper introduces L2M-AID, a novel framework for Autonomous Industrial Defense using LLM-empowered, Multi-agent reinforcement learning. L2M-AID orchestrates a team of collaborative agents, each driven by a Large Language Model (LLM), to achieve adaptive and resilient security. The core innovation lies …

Der #Friedhof in Bonfol hat doch eine beachtliche Grösse, und trumpft mit einer Art #Gebetshaus für den Kanton Jura auf, natürlich unter gütiger Überwachung Sankt Fromond, sozusagen Freimund. Hier heissen sie Henzelin (eher überraschend), Macquat, Biétry, und unvermeidlich -

Truth-Aware Decoding: A Program-Logic Approach to Factual Language Generation
Faruk Alpay, Hamdi Alakkad
https://arxiv.org/abs/2510.07331 https://arxiv.org…

Truth-Aware Decoding: A Program-Logic Approach to Factual Language Generation
This paper introduces Truth-Aware Decoding (TAD), a verification-oriented decoding scheme that aligns neural language generation with knowledge bases. Situated in the tradition of probabilistic program semantics for sequence models, TAD augments modern instruction-tuned systems with a lattice of semantic guards that operate at decode time. Our contributions are fourfold: (i) a constraint-based semantics that renders oracle filtering as a program-logic judgment, (ii) a proof that greedy selectio…

WIX - The Israeli Engine Behind Some of Your Favorite Websites
https://updates.techforpalestine.org/wix-the-israeli-engine-behind-some-of-your-favorite-websites/

The Colorful Cultures of Pre-Colonial Mindanao
Bridging the gap between what seems like ‘exotic’ Mindanao starts with understanding the culture of its people
https://www.esquiremag.ph/long-reads/features/mindano-culture-a2212-20200313-lfrm

[2025-10-10 Fri (UTC), 67 new articles found for cs.AI Artificial Intelligence]
toXiv_bot_toot

Today, there are 4971 public nodes listed on the Meshcore global map
#meshcore

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[8/8]:
- To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
Luo, Fan, Wang, He, Rahman, Abolmaesumi, Sigal

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[7/8]:
- Learning Neural Exposure Fields for View Synthesis
Niemeyer, Manhardt, Rakotosaona, Oechsle, Tsalicoglou, Tateno, Barron, Tombari

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[6/8]:
- Interpreting LLM-as-a-Judge Policies via Verifiable Global Explanations
Jasmina Gajcin, Erik Miehling, Rahul Nair, Elizabeth Daly, Radu Marinescu, Seshu Tirupathi

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[5/8]:
- Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks
Yang, Yang, Wen, Fu, Mei, Wu, Cai, Shen, Deng, Shi, Qiao, Li

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[4/8]:
- DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulation
Guowei Zou, Haitao Wang, Hejun Wu, Yukun Qian, Yuhang Wang, Weibing Li

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[3/8]:
- MeSH: Memory-as-State-Highways for Recursive Transformers
Yu, Shu, Wang, Zhang, Wu, Li, Long, Chen, Xu, Su, Zheng

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[2/8]:
- Label Semantics for Robust Hyperspectral Image Classification
Hassan, Roshni, Bari, Islam, Mohammed, Farazi, Rahman

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[1/8]:
- DUA-D2C: Dynamic Uncertainty Aware Method for Overfitting Remediation in Deep Learning
Md. Saiful Bari Siddiqui, Md Mohaiminul Islam, Md. Golam Rabiul Alam

How to Teach Large Multimodal Models New Skills
Zhen Zhu, Yiming Gong, Yao Xiao, Yaoyao Liu, Derek Hoiem
https://arxiv.org/abs/2510.08564 https://arxiv.org…

How to Teach Large Multimodal Models New Skills
How can we teach large multimodal models (LMMs) new skills without erasing prior abilities? We study sequential fine-tuning on five target skills while monitoring general ability on eight held-out benchmarks across three model families. We observe that apparent "forgetting" on held-out tasks after narrow fine-tuning can partly recover at later stages. We trace this behavior to a measurable shift in the output token distribution, manifested through a simple counting-bias probe that co-varies wit…

Agent Learning via Early Experience
Kai Zhang, Xiangchao Chen, Bo Liu, Tianci Xue, Zeyi Liao, Zhihan Liu, Xiyao Wang, Yuting Ning, Zhaorun Chen, Xiaohan Fu, Jian Xie, Yuxuan Sun, Boyu Gou, Qi Qi, Zihang Meng, Jianwei Yang, Ning Zhang, Xian Li, Ashish Shah, Dat Huynh, Hengduo Li, Zi Yang, Sara Cao, Lawrence Jang, Shuyan Zhou, Jiacheng Zhu, Huan Sun, Jason Weston, Yu Su, Yifan Wu

Agent Learning via Early Experience
A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains difficult in many environments, which either lack verifiable rewards (e.g., websites) or require inefficient long-horizon rollouts (e.g., multi-turn tool use). As a result, most current agents rely on supervised fine-tuning on expert data, which is challenging to s…

FlowSearch: Advancing deep research with dynamic structured knowledge flow
Yusong Hu, Runmin Ma, Yue Fan, Jinxin Shi, Zongsheng Cao, Yuhao Zhou, Jiakang Yuan, Xiangchao Yan, Wenlong Zhang, Lei Bai, Bo Zhang
https://arxiv.org/abs/2510.08521

FlowSearch: Advancing deep research with dynamic structured knowledge flow
Deep research is an inherently challenging task that demands both breadth and depth of thinking. It involves navigating diverse knowledge spaces and reasoning over complex, multi-step dependencies, which presents substantial challenges for agentic systems. To address this, we propose FlowSearch, a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning. FlowSearch is capable of strategically planning and expanding t…

CaRT: Teaching LLM Agents to Know When They Know Enough
Grace Liu, Yuxiao Qu, Jeff Schneider, Aarti Singh, Aviral Kumar
https://arxiv.org/abs/2510.08517 https://

CaRT: Teaching LLM Agents to Know When They Know Enough
Many tasks require learned models to strategically gather relevant information over multiple rounds of interaction before actually acting on a task. Strategic information gathering requires models to know not only how to effectively acquire information, but also when to stop gathering information and make a decision, in order to avoid overthinking or getting derailed when acting. In this paper, we formalize this problem and introduce Counterfactuals and Reasoning for Termination (CaRT), an appr…

AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents
Shangheng Du, Xiangchao Yan, Dengyang Jiang, Jiakang Yuan, Yusong Hu, Xin Li, Liang He, Bo Zhang, Lei Bai
https://arxiv.org/abs/2510.08511

AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents
Large language models (LLMs) have shown impressive performance in general programming tasks. However, in Machine Learning Engineering (MLE) scenarios such as AutoML and Kaggle competitions, achieving high performance depends heavily on expert intervention and repeated adjustments rather than simply generating correct code. When applied directly to these tasks, LLMs often lack fine-grained domain priors, and existing MLE approaches that use linear or tree-structured searches limit knowledge tran…

Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling
Bianca-Mihaela Ganescu, Suchir Salhan, Andrew Caines, Paula Buttery
https://arxiv.org/abs/2510.08470

Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling
Training vision-language models on cognitively-plausible amounts of data requires rethinking how models integrate multimodal information. Within the constraints of the Vision track for the BabyLM Challenge 2025, we propose a lightweight decoder-based architecture with (1) token-wise dynamic gating for adaptive fusion of linguistic and visual cues, (2) feature modulation and channel attention to maximise the utility of limited visual information and (3) auxiliary contrastive objectives for visua…

Revisiting Hallucination Detection with Effective Rank-based Uncertainty
Rui Wang, Zeming Wei, Guanzhang Yue, Meng Sun
https://arxiv.org/abs/2510.08389 https://

Revisiting Hallucination Detection with Effective Rank-based Uncertainty
Detecting hallucinations in large language models (LLMs) remains a fundamental challenge for their trustworthy deployment. Going beyond basic uncertainty-driven hallucination detection frameworks, we propose a simple yet powerful method that quantifies uncertainty by measuring the effective rank of hidden states derived from multiple model outputs and different layers. Grounded in the spectral analysis of representations, our approach provides interpretable insights into the model's internal re…

QAgent: A modular Search Agent with Interactive Query Understanding
Yi Jiang, Lei Shen, Lujie Niu, Sendong Zhao, Wenbo Su, Bo Zheng
https://arxiv.org/abs/2510.08383 https://

QAgent: A modular Search Agent with Interactive Query Understanding
Large language models (LLMs) excel at natural language tasks but are limited by their static parametric knowledge, especially in knowledge-intensive task. Retrieval-augmented generation (RAG) mitigates this by integrating external information. However, (1) traditional RAG struggles with complex query understanding, and (2) even search agents trained with reinforcement learning (RL), despite their promise, still face generalization and deployment challenges. To address these limitations, we prop…

LLMs Reproduce Human Purchase Intent via Semantic Similarity Elicitation of Likert Ratings
Benjamin F. Maier, Ulf Aslak, Luca Fiaschi, Nina Rismal, Kemble Fletcher, Christian C. Luhmann, Robbie Dow, Kli Pappas, Thomas V. Wiecki
https://arxiv.org/abs/2510.08338

LLMs Reproduce Human Purchase Intent via Semantic Similarity Elicitation of Likert Ratings
Consumer research costs companies billions annually yet suffers from panel biases and limited scale. Large language models (LLMs) offer an alternative by simulating synthetic consumers, but produce unrealistic response distributions when asked directly for numerical ratings. We present semantic similarity rating (SSR), a method that elicits textual responses from LLMs and maps these to Likert distributions using embedding similarity to reference statements. Testing on an extensive dataset compr…

Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries
Marius Dragoi, Ioana Pintilie, Florin Gogianu, Florin Brad
https://arxiv.org/abs/2510.08325 https://

Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm to improve Large Language Models on reasoning tasks such as coding, math or logic. To assess the reasoning boundary (the fraction of problems a model can solve) researchers often report Pass@k at large sampling budgets. Recent results reveal a crossover phenomenon: while RLVR models outperform the base model at small k values, the base model usually outperforms them when sampling a very large number of comp…

First Try Matters: Revisiting the Role of Reflection in Reasoning Models
Liwei Kang, Yue Deng, Yao Xiao, Zhanfeng Mo, Wee Sun Lee, Lidong Bing
https://arxiv.org/abs/2510.08308 h…

First Try Matters: Revisiting the Role of Reflection in Reasoning Models
Large language models have recently demonstrated significant gains in reasoning ability, often attributed to their capacity to generate longer chains of thought and engage in reflective reasoning. However, the contribution of reflections to performance improvement remains unclear. In this paper, we systematically analyze the rollouts of eight reasoning models on five mathematical datasets. We focus on reflective behaviours where the model has already produced an answer but continues reflecting …

Symmetry-Aware Fully-Amortized Optimization with Scale Equivariant Graph Metanetworks
Bart Kuipers, Freek Byrman, Daniel Uyterlinde, Alejandro Garc\'ia-Castellanos
https://arxiv.org/abs/2510.08300 …

Symmetry-Aware Fully-Amortized Optimization with Scale Equivariant Graph Metanetworks
Amortized optimization accelerates the solution of related optimization problems by learning mappings that exploit shared structure across problem instances. We explore the use of Scale Equivariant Graph Metanetworks (ScaleGMNs) for this purpose. By operating directly in weight space, ScaleGMNs enable single-shot fine-tuning of existing models, reducing the need for iterative optimization. We demonstrate the effectiveness of this approach empirically and provide a theoretical result: the gauge …

Co-TAP: Three-Layer Agent Interaction Protocol Technical Report
Shunyu An, Miao Wang, Yongchao Li, Dong Wan, Lina Wang, Ling Qin, Liqin Gao, Congyao Fan, Zhiyong Mao, Jiange Pu, Wenji Xia, Dong Zhao, Rui Hu, Ji Lu, Guiyue Zhou, Baoyu Tang, Yanqin Gao, Yongsheng Du, Daigang Xu, Lingjun Huang, Baoli Wang, Xiwen Zhang, Luyao Wang, Shilong Liu
https://

Co-TAP: Three-Layer Agent Interaction Protocol Technical Report
This paper proposes Co-TAP (T: Triple, A: Agent, P: Protocol), a three-layer agent interaction protocol designed to address the challenges faced by multi-agent systems across the three core dimensions of Interoperability, Interaction and Collaboration, and Knowledge Sharing. We have designed and proposed a layered solution composed of three core protocols: the Human-Agent Interaction Protocol (HAI), the Unified Agent Protocol (UAP), and the Memory-Extraction-Knowledge Protocol (MEK). HAI focuse…

Chain-of-Trigger: An Agentic Backdoor that Paradoxically Enhances Agentic Robustness
Jiyang Qiu, Xinbei Ma, Yunqing Xu, Zhuosheng Zhang, Hai Zhao
https://arxiv.org/abs/2510.08238

Chain-of-Trigger: An Agentic Backdoor that Paradoxically Enhances Agentic Robustness
The rapid deployment of large language model (LLM)-based agents in real-world applications has raised serious concerns about their trustworthiness. In this work, we reveal the security and robustness vulnerabilities of these agents through backdoor attacks. Distinct from traditional backdoors limited to single-step control, we propose the Chain-of-Trigger Backdoor (CoTri), a multi-step backdoor attack designed for long-horizon agentic control. CoTri relies on an ordered sequence. It starts with…

Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens
Yunlong Deng, Boyang Sun, Yan Li, Lingjing Kong, Zeyu Tang, Kun Zhang, Guangyi Chen
https://arxiv.org/abs/2510.08222

Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens
Due to their inherent complexity, reasoning tasks have long been regarded as rigorous benchmarks for assessing the capabilities of machine learning models, especially large language models (LLMs). Although humans can solve these tasks with ease, existing models, even after extensive pre-training and post-training at scale, still fail to perform reasoning reliably. In this paper, we revisit reasoning tasks from a causal perspective, seeking to understand their behavior in latent space and to off…

DODO: Causal Structure Learning with Budgeted Interventions
Matteo Gregorini, Chiara Boldrini, Lorenzo Valerio
https://arxiv.org/abs/2510.08207 https://arx…

DODO: Causal Structure Learning with Budgeted Interventions
Artificial Intelligence has achieved remarkable advancements in recent years, yet much of its progress relies on identifying increasingly complex correlations. Enabling causality awareness in AI has the potential to enhance its performance by enabling a deeper understanding of the underlying mechanisms of the environment. In this paper, we introduce DODO, an algorithm defining how an Agent can autonomously learn the causal structure of its environment through repeated interventions. We assume a…

The Tournament Tree Method for preference elicitation in Multi-criteria decision-making
Diego Garc\'ia-Zamora, \'Alvaro Labella, Jos\'e Rui Figueira
https://arxiv.org/abs/2510.08197

The Tournament Tree Method for preference elicitation in Multi-criteria decision-making
Pairwise comparison methods, such as Fuzzy Preference Relations and Saaty's Multiplicative Preference Relations, are widely used to model expert judgments in multi-criteria decision-making. However, their application is limited by the high cognitive load required to complete $m(m-1)/2$ comparisons, the risk of inconsistency, and the computational complexity of deriving consistent value scales. This paper proposes the Tournament Tree Method (TTM), a novel elicitation and evaluation framework tha…

Measuring What Matters: The AI Pluralism Index
Rashid Mushkani
https://arxiv.org/abs/2510.08193 https://arxiv.org/pdf/2510.08193

Measuring What Matters: The AI Pluralism Index
Artificial intelligence systems increasingly mediate knowledge, communication, and decision making. Development and governance remain concentrated within a small set of firms and states, raising concerns that technologies may encode narrow interests and limit public agency. Capability benchmarks for language, vision, and coding are common, yet public, auditable measures of pluralistic governance are rare. We define AI pluralism as the degree to which affected stakeholders can shape objectives, …

R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
Yi Lu, Jianing Wang, Linsen Guo, Wei He, Hongyin Tang, Tao Gui, Xuanjing Huang, Xuezhi Cao, Wei Wang, Xunliang Cai
https://arxiv.org/abs/2510.08189

R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
Recent trends in test-time scaling for reasoning models (e.g., OpenAI o1, DeepSeek-R1) have led to remarkable improvements through long Chain-of-Thought (CoT). However, existing benchmarks mainly focus on immediate, single-horizon tasks, failing to adequately evaluate models' ability to understand and respond to complex, long-horizon scenarios. To address this incomplete evaluation of Large Reasoning Models (LRMs), we propose R-HORIZON, a method designed to stimulate long-horizon reasoning beha…

Prepared mind, fast response: A temporal decoupling framework for adaptive knowledge orchestration in open-domain dialogue
Jinling Gan, Churong Liang, Runnan Li
https://arxiv.org/abs/2510.08175

Prepared mind, fast response: A temporal decoupling framework for adaptive knowledge orchestration in open-domain dialogue
The latency-quality tradeoff is a fundamental constraint in open-domain dialogue AI systems, since comprehensive knowledge access necessitates prohibitive response delays. Contemporary approaches offer two inadequate solutions: lightweight instruct models achieve sub-second latency but lack reasoning depth, while tool-augmented ReAct agents enhance factuality through external knowledge at the cost of synchronous execution that blocks interaction during re- trieval processes. PMFR is thus propos…

Can Risk-taking AI-Assistants suitably represent entities
Ali Mazyaki, Mohammad Naghizadeh, Samaneh Ranjkhah Zonouzaghi, Amirhossein Farshi Sotoudeh
https://arxiv.org/abs/2510.08114

Can Risk-taking AI-Assistants suitably represent entities
Responsible AI demands systems whose behavioral tendencies can be effectively measured, audited, and adjusted to prevent inadvertently nudging users toward risky decisions or embedding hidden biases in risk aversion. As language models (LMs) are increasingly incorporated into AI-driven decision support systems, understanding their risk behaviors is crucial for their responsible deployment. This study investigates the manipulability of risk aversion (MoRA) in LMs, examining their ability to repl…

From Ethical Declarations to Provable Independence: An Ontology-Driven Optimal-Transport Framework for Certifiably Fair AI Systems
Sukriti Bhattacharya, Chitro Majumdar
https://arxiv.org/abs/2510.08086

From Ethical Declarations to Provable Independence: An Ontology-Driven Optimal-Transport Framework for Certifiably Fair AI Systems
This paper presents a framework for provably fair AI that overcomes the limits of current bias mitigation methods by systematically removing all sensitive information and its proxies. Using ontology engineering in OWL 2 QL, it formally defines sensitive attributes and infers their proxies through logical reasoning, constructing a sigma algebra G that captures the full structure of biased patterns. Fair representations are then obtained via Delbaen Majumdar optimal transport, which generates var…

AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment
Xiaochong Lan, Jie Feng, Yinxing Liu, Xinlei Shi, Yong Li
https://arxiv.org/abs/2510.08081

AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment
Ranking online reviews by their intrinsic quality is a critical task for e-commerce platforms and information services, impacting user experience and business outcomes. However, quality is a domain-dependent and dynamic concept, making its assessment a formidable challenge. Traditional methods relying on hand-crafted features are unscalable across domains and fail to adapt to evolving content patterns, while modern deep learning approaches often produce black-box models that lack interpretabili…

Multi-Condition Conformal Selection
Qingyang Hao, Wenbo Liao, Bingyi Jing, Hongxin Wei
https://arxiv.org/abs/2510.08075 https://arxiv.org/pdf/2510.08075

Multi-Condition Conformal Selection
Selecting high-quality candidates from large-scale datasets is critically important in resource-constrained applications such as drug discovery, precision medicine, and the alignment of large language models. While conformal selection methods offer a rigorous solution with False Discovery Rate (FDR) control, their applicability is confined to single-threshold scenarios (i.e., y > c) and overlooks practical needs for multi-condition selection, such as conjunctive or disjunctive conditions. In th…