Multi-Agent Systems and Negotiation

Latest papers

• Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original Premise

  Ziang Ni, Peng Zou · 5 October 2026

  Multi-agent debate is increasingly used to reach consensus among LLM agents, yet agents often yield to a unanimous majority. When an agent changes its answer, has it changed its mind or only its statement? We study this with two-hop factual questions whose intermediate entity (the bridge, e.g. the c…

• Ask, Relax, or Act? Evaluating Actionable Indeterminacy in LLM Preference Reasoning

  Ang Li, Yue Lin, Feifei Kou, Zhan Su, Prayag Tiwari, Wenhao Li, Shuhui Zhu, Hongyuan Zha, Baoxiang Wang · 5 October 2026

  An LLM agent can recognize uncertainty yet still choose the wrong next step: asking when action is already justified, or seeking clarification when the constraints must change. We formalize actionable indeterminacy: act when an accepted action is shared across all admissible preferences or objective…

• Toward SLM-based agentic task-tool intent matching

  Chiara Troiani, Arash Salarian, Majed El Helou, Benjamin Ryder, Jean Diaconu, Herv\'e Muyal, Marcelo Yannuzzi · 5 October 2026

  Tool-equipped AI agents use tool calls to access data and act on external systems. Horizontal growth of agentic systems increases the number of these interactions, and further motivates the need for automated, per-call oversight that can operate at low latency and/or on-prem. Conventional authorizat…

• When Numbers Start Talking: Numerical Signalling and Strategic Behaviour Among LLMs

  Alessio Buscemi, Daniele Proverbio, Alessandro Di Stefano, The Anh Han, German Castignani, Pietro Li\`o · 5 October 2026

  Large language model (LLM)-based agents increasingly operate in multi-agent systems (MAS) characterised by strategic interaction. However, little is known about whether, and to what extent, different types of messages affect the outcomes of strategic games. By investigating AI agents based on four p…

• How to Have a Sensitive Debate: An Instance-Optimal Protocol for AI Debate

  Jiawei Li, Zhiyang Xun, Lijie Chen, Jonah Brown-Cohen · 5 October 2026

  As powerful AI systems reach and sometimes surpass the abilities of human experts across a range of cognitively demanding tasks, the problem of accurate oversight and supervision of these systems has become increasingly urgent. One promising approach is AI debate, which seeks to leverage a debate be…

• DeReAct: Decomposed Reasoning and Acting for Reliable AI Agents

  Ajay Vohra, Tao Chen, Neeti Narayan, Caron Zhang · 5 October 2026

  ReAct-based agents typically rely on a single LLM policy to propose actions, interact with the environment, and decide when a task is complete. This coupling makes action authorization and completion control difficult to enforce independently, allowing errors to propagate and unsupported completion …

• Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents

  Yu Li, Zheng Zhang, Xin Liu, Shengtian Yang, Guangfeng Cai, Lei Feng · 5 October 2026

  Large language models (LLMs) rely on long-horizon tool invocation sequences for complex tasks, where each invocation can alter the task state and condition subsequent decisions. In long-horizon tool use, final-outcome rewards provide weak credit assignment over long interaction traces. Step-level re…

• Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses

  Jiawei Li · 5 October 2026

  Agent harnesses make many small, typed decisions per task: which model to call, which tool to use, whether retrieved text is relevant, whether an input carries an injection. System-1 decision models answer such questions in a single forward pass with class probabilities, promising large cost and lat…

• Peer Influence across Heterogeneous AI Models

  Frida N{\o}hr Laustsen, Marie Haahr Petersen, Victoria Popa, Ariel Flint, Romualdo Pastor-Satorras, Andrea Baronchelli, Luca Maria Aiello · 5 October 2026

  When two AI agents disagree, who persuades whom? As multi-agent systems increasingly combine language models of different families and sizes, the answer can determine which judgments survive interaction. Measuring persuasion as the probabilistic shift in an agent's decision after a single exchange w…

• Right Answers, Wrong States: Hidden Information Failures in Multi-Agent Collaboration

  Herun Wan, Jiaying Wu, Minnan Luo, Zihan Ma, Fanxiao Li, Nancy F. Chen, Min-Yen Kan · 2 October 2026

  Multi-agent systems are often judged by whether they reach the correct answer. This can miss a distinct failure: collaboration may leave behind a corrupted information state even when the immediate decision is correct. We call this an off-query failure. To study this failure in collaborative decisio…

• My FAULT: Self-Diagnosis as Credit Assignment in Self-Evolving Agentic Reinforcement Learning

  Yihua Zhu, Qianying Liu, Weixu Qiao, Xuan Ren, Weiwei Xu, Wenbo Li, Wei Wang, Ruijia Chen, Xinmiao Luan, Yin Luo, Hao Huang, Xiang Zheng, Hidetoshi Shimodaira · 2 October 2026

  Agentic reinforcement learning (RL) has emerged as a powerful approach for training large language model agents on multi-step tasks, yet reliance on terminal outcome rewards creates two credit-assignment problems, particularly in long-horizon tasks. First, same-outcome rollout groups provide no lear…

• Beyond Leaderboards: Tokenomics of Agentic Small Language Model Ensembles

  Alexei N. Skurikhin, Emily M. Taylor, Nathan A. DeBardeleben · 2 October 2026

  As large language models (LLMs) move from standalone assistants into agentic workflows, evaluation must extend beyond scalar leaderboard accuracy to account for operational reliability, cost, latency, and token efficiency. We use an agentic ensemble of small language models (SLMs) with an SLM-judge-…

• LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios

  Bingxi Zhao, Lin Geng Foo, Ping Hu, Christian Theobalt, Hossein Rahmani, Jun Liu · 2 October 2026

  Recent advances in LLM-based agents highlight the importance of their reasoning frameworks, which guide the problem-solving process in diverse ways. This survey introduces a unified formal language to systematically categorize these frameworks at three compositional levels: single-agent, tool-based,…

• Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning

  Dayu Wang, Yutong Liu, Jiaye Yang, Weikang Li, Jiahui Liang, Yang Li · 2 October 2026

  Recent advances in multi-agent systems highlight the potential of specialized small agents that collaborate via division of labor. Existing tool-integrated reasoning systems, however, often follow a single-agent paradigm in which one large model interleaves long-horizon reasoning with precise tool o…

• LLM-Driven Multi-Agent Control for Skill-Based Smart Manufacturing

  Kay K\"ohle, Darko Anicic, Thomas A. Runkler, Ren\'e Graf · 2 October 2026

  Factories are shifting toward smaller lot sizes with high product customization, requiring frequent re-programming of flexible and reconfigurable automation systems. LLM-based agents can be deployed in two complementary roles: Offline, they generate deterministic production sequences, reducing progr…

• Understanding Issues, Causes and Solutions in Open-Source LLM-based Multi-Agent Systems

  Asad Ur Rehman, Syed Mohammad Kashif, Ruiyin Li, Peng Liang, Zengyang Li, Arif Ali Khan · 2 October 2026

  With the advancement of LLM-based multi-agent systems (MAS), an increasing number of opensource projects are adopting multi-agent architectures as the foundation of their core functionality. Although research and practice on MAS have attracted considerable attention, limited studies have explored th…

• Global Coherence: When Every Agent Is Right and the Team Is Still Wrong - A Local-to-Global Semantic Foundation for Multi-Agent Collaboration

  Xin Heng · 2 October 2026

  AI agents can each make locally valid decisions yet jointly produce an invalid result. We call this the global coherence problem: a failure of shared state, not merely of model intelligence. Our Observation-Aliasing Impossibility Theorem gives the exact boundary. A policy can guarantee a valid act…

• Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries

  Ionel Eduard Stan, Paolo Napoletano · 2 October 2026

  A multi-LLM \emph{council} lets several large language models (LLMs) deliberate on a question and return an answer together with a confidence estimate. As these systems become increasingly used for reasoning, that confidence should represent a calibrated \emph{probability of being correct}, and the …

• Code Owns the Simulation, Jev Owns the Evaluation

  Yaodong Yang, Hongyao Tang, Yi Ma, Xingyu Fan, Weixun Wang, Jinpeng Li, Tianpei Yang · 2 October 2026

  Judgment models such as \jev{} return, in a single call and without reasoning text, a probability for each described option. This makes them attractive as an agent's action-selection layer, but it is unclear which decisions they can be trusted with. We test \jev{} on reflection tests, one-shot matri…

• Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States

  Yu Luo, Jiamin Jiang, Yimin Zuo, Xidao Wen, Rongchen Gao, Yongqian Sun, Shenglin Zhang, Guiyang Liu, Cheng Zhang, Fang Situ, Qi Zhou, Dan Pei · 2 October 2026

  Large language model (LLM) agents can now undertake increasingly complex tasks, but the way they organize interaction history into memory does not ensure a coherent understanding of the current world. We introduce PoS, an inference-time framework that constructs and continually maintains explicit be…

• Verify Claims, Not Scores: Evidence-Based Verification of Modular Agents

  Ali Atiah Alzahrani · 2 October 2026

  When developers change one component of an agent, such as its controller, a learned model or its verifier, they usually judge the change by an aggregate task score. That score cannot tell whether improvement was attainable, which component lost value, or what the agent's own checks certify. We intro…

• Revision-Aware Independent Agent Graphs for Dynamic Reasoning

  Yan Luo, Selim-Antoine Lali, Jeremy Moebel, Iliass Khoutaibi, Ahmadou Aidara, Mengyu Wang · 2 October 2026

  Conventional reasoning protocols present a fixed, preselected task, so they cannot test whether an agent propagates relevant updates, preserves unaffected work, or reconstructs a historical task binding. We therefore study \emph{dynamic task routing}, in which an event stream revises task bindings a…

• Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay

  Haotian Chen, Bowen Ye, Yuning Zhang, Jingkun Yu · 2 October 2026

  Concurrent actions in large language model (LLM) agent environments require arbitration even when each proposal is individually valid. We implement a typed snapshot-settlement contract and audit three distinct properties: order sensitivity, useful progress, and replay consistency. Five settlement po…

• Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems

  Shixuan Li, Wei Yang, Peiyu Zhang, Anzhe Cheng, Heng Ping, Paul Bogdan · 2 October 2026

  Multi-agent communication aims to help agents benefit from one another's information. Yet improvements in system performance leave a fundamental ambiguity: do they reflect effective communication, a favorable agent architecture, or simply additional reasoning? Because communication methods are commo…

• Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization

  Xuehang Guo, Haoyu Wang, Shengyu Chen, Zach Chen, Wei Cheng, Qingyun Wang, Haifeng Chen · 2 October 2026

  Large language models (LLMs) increasingly construct multi-agent workflows that decompose a complex task and assign specialist agents from a pool. However, building such a workflow well remains challenging: how finely to divide the task, which agent to trust with each subtask, and when to create a ne…