Multi-Agent LLMs

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

22 papers in the last four weeks, up 144% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 212

Jun 14, 2026cs.AI

Multi-agent Framework for Time-Sensitive Complementary Collaboration in Minecraft

We present TickingCollabBench, a Minecraft-based multi-agent benchmark for a novel class of time-sensitive complementary collaboration tasks. Our benchmark reflects four core characteristics of real-world collaboration: agent heterogeneity, mandatory collaboration, dynamic environments, and strict real-time constraints with failure risks. To enable this, we develop the TickingCollab framework, which supports the generation of diverse dynamic environments and abstracts Minecraft's primitive APIs to enable declarative YAML task specifications for composing these events. Building on this, we design a feasibility-aware automated benchmark generation pipeline, where an LLM drafts structurally diverse task configurations and feasibility verifier filters out invalid ones using approximate constraints. Evaluations demonstrate that lang latency and inherent difficulty of coordinating under partial observability and agent heterogeneity cause LLMs to frequently fail under dynamic environments and fall significantly short of a global-knowledge oracle.

Juheon Yi, Jinglu Wang, Xiaoyi Zhang +1

Microsoft Research Asia

Multi-Agent Coordination Multi-Agent Collaboration AI Agent Benchmarks Multi-Agent LLMs

Jun 11, 2026cs.AI

Reward Modeling for Multi-Agent Orchestration

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) require effective orchestration to coordinate specialized agents, yet training such orchestrators is hindered by limited supervision and high computational cost. We propose Orchestration Reward Modeling (OrchRM), a self-supervised framework for evaluating orchestration quality without human annotations. OrchRM leverages intermediate artifacts from multi-agent executions to construct win-lose pairs for Bradley-Terry reward model training. Unlike existing MAS test-time scaling and orchestrator training frameworks that rely on costly sub-agent rollouts, OrchRM operates directly at the orchestration level, enabling efficient and high-performing reward-guided orchestrator training and MAS test-time scaling. OrchRM improves training efficiency by up to 10x in token usage while improving MAS test-time scaling performance by up to 8% in accuracy. These gains consistently transfer across multiple domains, including mathematical reasoning, web-based question answering, and multi-hop reasoning, demonstrating orchestration-level reward modeling as a scalable direction for robust multi-agent orchestration. Code will be available at https://github.com/Wang-ML-Lab/OrchRM.

King Yeung Tsang, Zihao Zhao, Vishal Venkataramani +5

Rutgers University · Salesforce AI Research

Reward Modeling Multi-Agent Orchestration Self-Supervised Learning Multi-Agent LLMs

Jun 11, 2026cs.MA

See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents

Language-model agents build internal representations of the information they observe and the reasoning they perform. Sharing these representations offers a way to communicate both source information and reasoning across agents. For agents built from different models, this requires aligning their representations while preserving information useful to the receiver. We study this problem through KV-cache communication, examining how an agent uses internal states shared by other agents, with or without direct access to the information that other agents observed. A controlled self-communication study shows that cache pruning causes substantially greater degradation when the receiving agent lacks access to that information. We use this finding to guide dense cross-model cache alignment, combining positional disentanglement and KV-group transformations with reconstruction followed by generation training. Across six directed Qwen3 pairs, aligned caches improve in-domain accuracy over text communication when both agents observe the same input, with fewer estimated inference FLOPs. Experiments with three-agent document sharing and Mistral-to-Qwen transfer further demonstrate that aligned caches can carry information across both multiple separate observations and different model families.

Siyi Chen, Xiaoyan Zhang, Meng Wu +7

University of Michigan · NVIDIA · University of Pennsylvania +2

Multi-Agent Communication Multi-Agent LLMs

Jun 11, 2026cs.CL

ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages

Multimodal Large Language Models (MLLMs) have shown promising reasoning capabilities in general domains, yet their performance remains limited in specialized settings such as healthcare, especially in multilingual and low-resource scenarios. This gap is critical in regions like rural India, where patients often express complex medical queries in native Indic languages and rely on multimodal inputs such as medical images. Existing English-centric MLLMs struggle to support such use cases, limiting equitable access to AI-driven healthcare assistance. To address this challenge, we introduce ArogyaBodha, a large-scale multilingual multimodal medical question-answer dataset constructed from eight heterogeneous sources, covering 31 body systems, six imaging modalities, and 21 clinical domains across English and seven major Indian languages. We further propose ArogyaSutra, an actor-critic-based multi-agent framework that integrates tool grounding with dual-memory mechanisms for step-wise, reasoning-aware decision making, and uses stored actor-critic simulation trajectories for distillation. Experiments show that our dataset and framework improve multilingual medical reasoning accuracy across all Indic languages, with ablations validating the contribution of each component. The source code and dataset are available at: https://iitp-cse.github.io/ArogyaSutra/

Tanmoy Kanti Halder, Akash Ghosh, Subhadip Baidya +2

1Indian Institute of Technology Patna · 3Prasannadeb Women’s College · 2Indian Institute of Technology Kanpur

Multilingual Language Models RL for Language Model Reasoning Multimodal QA Medical QA Multi-Agent LLMs Medical LLMs

Jun 11, 2026cs.AI

Nous: An Attempt to Extract and Inject the Cognition Behind Prediction-Market Behavior

As LLM agents proliferate in prediction markets and collective decision-making, they risk a cognitive monoculture: agents built on shared foundation models produce correlated forecasts, and recent measurement finds frontier-model errors correlated at r ~ 0.77. We ask whether human cognitive diversity can be recovered from behavior and transferred to LLM agents. Nous extracts a structured eight-dimension behavioral profile from real Polymarket trading activity and injects it into agents through prompts. Our central finding is a dissociation between the two halves of that pipeline. Extraction works, partially: across 100 wallets, 8 of 14 parameters are temporally stable (split-half ICC >= 0.5, bootstrap CI lower bound > 0.3; contrarian score reaches ICC ~ 0.9); wallets are identifiable from their profiles well above chance (top-1 retrieval 17-22% vs. 1% chance); and two of four pre-specified dimensions rank-correlate with future realized profit out-of-sample, though the correlations do not survive behavioral-confound controls. Prompt-level injection does not measurably transmit it: on a semantic embedding metric, structured injection shows no significant advantage over a length-matched control on any model, and the diversity it induces neither reduces ensemble error correlation nor improves Brier score -- a null that persists across exploratory checks on sampling temperature, profile diversity, and question difficulty. Measuring the prompts themselves locates the compression before the model: the structure-to-narrative translator emits near-uniform prompts whose spread does not track profile spread. We position Nous as measuring the cognitive-monoculture problem and the limits of a prompt-level remedy, motivating deeper, below-the-prompt injection (fine-tuning, activation steering). Code, frozen profiles, prompts, and model outputs: https://github.com/WillChienT/nous-paper

Haowei Qian

Independent Researcher

Cognitive Modeling LLM Agent Evaluation Multi-Agent LLMs Prediction Markets

Jun 11, 2026cs.AI

(Human) Attention Is (Still) All You Need: Human oversight makes AI-assisted social science reliable

Large language models (LLMs) are increasingly used for tasks once reserved for trained researchers, including hypothesis generation, specification choice, and drafting conclusions. We argue that the reliability of AI-assisted research depends not only on model capability, but also on how cognitive labour is structured between humans and machines. We study this problem through Human-in-the-Loop Economic Research (HLER), a decision architecture based on pre-commitment, decision sequencing, accountability, and attention allocation. In a pre-specified 2*4 factorial experiment with 280 complete research runs across four datasets, an unconstrained multi-agent baseline produced critical failures in 72% of runs. Using the same underlying model, the same agent decomposition, and identical prompts for the shared reasoning agents, HLER reduced the failure rate to 16% by imposing three architectural commitments: LLMs reason but do not execute data work, data and estimation are handled deterministically, and three human decision gates bind the workflow. Fisher's exact test rejects equality of failure rates at p<0.001. Reliability gains were largest on the least publicly represented dataset, a Qing-dynasty population register, consistent with a task-based production model with Frechet-distributed output quality. An 80-run ablation suggests that deterministic computation and human gates contribute independently, with exploratory evidence of complementarity. We interpret HLER as a research harness rather than an autonomous AI scientist: it sharply reduces failures, makes residual weaknesses more visible, and prevents unreliable claims from being advanced as publication-ready outputs.

Chen Zhu, Xiaolu Wang, Weilong Zhang

China Agricultural University · University of Cambridge

AI Agent Reliability AI-Assisted Scientific Research Human-in-the-Loop AI LLM Reliability Human Oversight of AI Multi-Agent LLMs+1

Jun 10, 2026cs.MA

Smarter Saboteurs, Better Fixers: Scaling & Security in Linear Multi-Agent Workflows

As LLM-based multi-agent systems (MAS) are deployed in the wild, the resilience of their collaboration structures against adversarial compromise becomes a critical safety concern. Attackers may leverage prompt-injection or jailbreaking to sabotage individual agents within MAS workflows, but the interaction between model scaling and system-level resilience remains poorly understood. This paper investigates how model scale affects the security of linear multi-agent workflows. Our experiments across scales of two open-weight model families on the HumanEval benchmark reveal a compliance-correction symmetry: larger models are far more likely to faithfully execute malicious instructions, with the control-to-malicious performance drop reaching 53.7pp at 27B in uncorrected pipelines. However, appending a lightweight terminal Fixer stage collapses this to 0.6pp and restores statistical parity with control-level performance, demonstrating that strictly linear collaboration structures can be viable and resilient to adversaries at this scale, and suggesting that the brittleness previously attributed to linear topology may stem from a lack of correction.

Timothy McAllister, Sina Abdidizaji, Ivan Garibay +1

Department of Computer Science, University of Central Florida, Orlando, FL, USA · Department of Industrial Engineering, University of Central Florida, Orlando, FL, USA

AI Agent Security LLM Agent Security Prompt Injection Attacks on AI Agents Multi-Agent System Security Multi-Agent LLMs

Jun 10, 2026cs.SE

Exploration Structure in LLM Agents for Multi-File Change Localization

Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue. Most AI agents explore repositories linearly, that is, visiting one directory or file per step. We postulate that this is a structural mismatch for changes that span several subsystems. We compare linear sequential exploration against non-linear, domain-scoped parallel agentic exploration. Using SWE Bench Pro as initial benchmark, we focus on ansible as an exemplar. We construct an approach for persistent-session evaluation of GitHub issues anchored at a single base commit. We compare our non-linear domain-agent file traversal system against a base LLM without direct repository access, a single agent Recursive Language Model (RLM) baseline with a persistent Python REPL and an external CLI baseline using Codex 5.5 High. Domain scoped parallel agent spawning with a small Haiku-class model achieves the highest micro F1 among Haiku class models by a large margin. Domain-agents is the second highest behind only the much larger Codex 5.5 High on our own expanded benchmark including over more recent PRs from 2025 and 2026. On the original, curated, 2020 SWE-bench Pro benchmark, a larger Sonnet plain LLM baseline attains higher micro F1 by predicting few files, leading to higher precision, but at significantly lower all gold recall. We also present three additional findings. First, documentation evolution is a latent dependency unresolved by any approach. Second, naive file system access can degrade localization driven by test-file over prediction. Lastly, forced multi-agent consultation does not measurably help and raises token cost substantially.

Akeela Darryl Fattha, Kia Ying Chua, Lingxiao Jiang +1

School of Computing and Information Systems Singapore Management University Singapore

Software Engineering Software Engineering Agents AI Coding Agents Multi-Agent LLMs

Jun 10, 2026cs.CL

Multi-Agent Reasoning with Adaptive Worker Allocation for Stance Detection

Stance detection requires identifying an author's position toward a target, often from short-form texts where stance is implicit, indirect, or rhetorically framed. Although large language models (LLMs) achieve strong performance on this task, single-pass prompting can be brittle when multiple interpretations are plausible. Existing aggregation strategies, such as majority voting or self-consistency, improve robustness by combining labels, but they discard the intermediate reasoning needed to resolve conflicting interpretations. We introduce a multi-agent reasoning framework with adaptive worker allocation for stance detection that shifts aggregation from label-level voting to reasoning-level synthesis. The framework employs a Manager-Worker architecture in which a Manager adaptively allocates a variable number of Worker agents based on input complexity. Each Worker analyzes the input from a distinct perspective and produces a reasoning-only explanation without emitting a stance label; the Manager then synthesizes these explanations to produce the final prediction. We evaluate the proposed framework on SemEval-2016, P-Stance, and COVID-19 Stance using Llama, Mistral, and Gemini. Results show that the framework yields the largest gains on implicit and context-dependent stance cases, achieving 86.07 Macro-F1 on COVID-19 and 82.90 on SemEval-2016, while remaining competitive on more explicit stance datasets such as P-Stance. These findings suggest that adaptive reasoning-level aggregation is most beneficial when stance cannot be reliably inferred from surface cues alone.

Meysam Sabbaghan, Arman Zareian Jahromi, Doina Caragea

Department of Computer Science Kansas State University

Stance Detection Multi-Agent Reasoning Multi-Agent LLMs

Jun 9, 2026cs.CV

CoCoSI: Collaborative Cognitive Map Construction for Spatial Intelligence

Spatial intelligence is a key frontier for multimodal large language models (MLLMs), enabling them to reason about the physical world from visual experience. Inspired by human spatial cognition, recent approaches construct grid-based cognitive maps from multi-frame visual inputs to maintain coherent spatial representations over time. However, limited context lengths still challenge spatial understanding, while existing methods, such as long-context modeling and external memory, often require architectural changes, memory modules, or finetuning, limiting their applicability to off-the-shelf pretrained MLLMs. This motivates a lightweight, model-agnostic method for preserving spatial information beyond the native context window. To this end, we propose a plug-and-play multi-agent framework that collaboratively constructs cognitive maps as structured spatial memory, enhancing the spatial understanding of arbitrary pretrained MLLMs without architectural modification or additional training. Our framework features local-global agent coordination, cognitive map construction with atomic commits, and cross-agent verification. Extensive experiments demonstrate that our method achieves superior performance on spatial understanding tasks while remaining fully training-free. Code will be released.

Yiming Zhang, Ruoxuan Cao, Zhihang Zhong

2Cornell University · 1Shanghai Jiao Tong University

Multimodal Large Language Models Multi-Agent LLMs Spatial Reasoning Memory-Augmented Language Model Agents Multimodal Understanding

Jun 9, 2026cs.CR

Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs

Large Language Models (LLMs) in multi-turn interactions maintain evolving context rather than generating isolated responses, making them vulnerable to prompt-injection and context-poisoning attacks in which locally plausible adversarial fragments gradually distort reasoning trajectories. Existing defenses mainly filter individual outputs and often ignore context evolution across turns, leaving long-horizon reasoning exposed. Although the Model Context Protocol (MCP) standardizes context exchange and tool invocation, it functions as a passive routing layer and does not enforce contextual stability. To address these limitations, we introduce the Game-Theoretic Secure Model Context Protocol (GT-MCP), a controller-driven multi-agent method that treats context management as a closed-loop dynamical process. GT-MCP coordinates three heterogeneous LLM agents and selects outputs through a trust function that jointly evaluates causal consistency against a validated context graph, semantic agreement among agents, and distributional drift over time. When instability is detected, a rollback-based self-healing mechanism restores the validated context and prevents unsupported fragments from propagating. Empirical evaluation over 500 interaction turns under an adaptive adversarial threat model shows that contextual drift remains bounded in 99.6% of turns, with recovery required in only 0.4%. Per-turn utility remains tightly concentrated, with median = -0.19, P05 = -0.72, and P95 = 0.30; severe degradation below -1 occurs in only 0.4% of cases, and no injection attempt succeeds at the controller level. Selected outputs maintain stable win rates above 98%, and computational overhead remains predictable, with latency per token = 1.63e-3 s.

Saeid Jamshidi, Amin Nikanjam, Arghavan Moradi Dakhel +2

SWAT Laboratory, Polytechnique Montréal, Montréal, QC, Canada · Huawei Distributed Scheduling and Data Engine Lab, Montr´eal, QC, Canada

Adversarial Attacks on LLMs Multi-Agent Control Adversarial Robustness of Language Models Prompt Injection Attacks on LLMs Multi-Agent LLMs LLM Context Management

Jun 8, 2026cs.CL

Civil Court Simulation with Large Language Models

Court simulation bridges legal education and judicial practice, yet human-based simulations are costly and difficult to scale. Large language models (LLMs) offer a scalable alternative, but existing court-simulation research mainly focuses on criminal cases. Civil litigation is more common in practice and harder to simulate because its claims, liability, and remedies are more flexible. We present a multi-agent court simulation framework for Chinese civil cases. The framework organizes role-based interaction through a five-stage civil trial procedure and integrates memory module and statute retrieval to support long-process adjudication. Experiments show that the framework produces reliable civil judgments, with clear strengths in liability allocation and multi-item adjudication. Further experiments show that memory quality substantially affects downstream simulation quality. Through a five-layer factor framework, we analyze how legal grounding, information conditions, judicial capability and role orientation, organizational pressure, and social context affect the framework's reliability and behavior. These results support the effectiveness of the proposed framework for civil court simulation. The dataset and code are available at: https://github.com/foggpoy/Civil-Court.

Yifan Chen, Haitao Li, Kaiyuan Zhang +3

Beijing University of Posts and Telecommunications, Beijing, China · Tsinghua University, Beijing, China

Multi-Agent LLMs Legal Reasoning Memory-Augmented Language Model Agents

Jun 7, 2026cs.AI

Scaffold Effects on GAIA: A Controlled Comparison

Published agent capability scores conflate what a model can do with what its scaffold lets it do, and the magnitude of this elicitation gap is not well characterized under controlled conditions. This study executes a pre-registered controlled comparison of three scaffolds (ReAct, a Planner-Actor-Rater multi-agent design, and planner-then-executor) across five models from three providers (Claude Opus 4.7, Sonnet 4.6, Haiku 4.5; Gemini 3.1 Pro Preview; GPT-5.5) on GAIA validation Levels 1 and 2, holding tasks and conditions fixed, with three attempts per question. Scaffold choice alone moves measured accuracy by as much as 28 percentage points within a single model (Opus, Level 2, robust slice), confirming the pre-registered hypothesis that scaffold variation produces gaps of at least 10 points. The pre-registered prediction that more capable models would be less scaffold-sensitive is rejected in direction: scaffold effects vary significantly by model in every dataset slice, but the most capable Anthropic model gains the most from structured scaffolds at the harder level, and tier-scaling holds only at Level 1 under the robust slice. The multi-agent advantage over ReAct at Level 2 appears within the Anthropic family but not for the cross-provider models, making model family rather than capability tier the conditioning variable, and the predicted planner-executor advantage on file-reading tasks is falsified. Structured scaffolds make fewer tool calls yet recover more often from mid-trajectory errors at the harder level, and a single cell (Gemini with planner-then-executor) is the cheapest at both levels and the most accurate at Level 2. These results indicate that single-scaffold capability numbers are scaffold-conditional estimates and that the elicitation gap is not guaranteed to shrink as models improve.

Jason Starace

Independent Researcher

LLM Agent Evaluation AI Agent Benchmarks Multi-Agent LLMs Agent Benchmarks

Jun 6, 2026cs.HC

"So There's a Catch-22 Here": How Early Adopters Who Build Multi-Agent LLM Systems Conceptualize Transparency

Multi-agent large language model (LLM) systems are rapidly emerging, yet transparency, a cornerstone of responsible AI, remains under-defined in these distributed architectures, which have complexities of inter-agent coordination and orchestration. In this paper, we present one of the first empirical study of how early adopters of multi-agent LLM systems, who are both the builders and users, understand and practice transparency. We conducted semi-structured interviews with 13 early adopters in [Large Technology Organization] and applied thematic analysis to identify recurring patterns. Participants articulated divergent yet complementary framings of transparency, including reproducibility, debugging, boundary-setting, visualization, and auditing. These perspectives spanned questions of what transparency entails, why it matters, and how it is achieved. We synthesize these into a multidimensional framework, which is developer, user, and governance-focused positioning transparency as a situated socio-technical practice that informs future HCI and AI design and research around aligning expectations and capacities of their intended audiences.

Suchismita Naik, Samir Passi, Mihaela Vorvoreanu +2

Purdue University, USA · Cornell University, USA · Microsoft Research, USA

Multi-Agent LLM Systems AI Agent Governance Multi-Agent LLMs

Jun 6, 2026cs.LG

DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination

Multi-agent large language model (LLM) systems often fail to reliably outperform a single strong model equipped with best-of-N sampling. We argue that a core source of this instability is ill-posed equilibrium selection: current systems specify what information agents share, but not which coordination convention should be selected. We formalize a broad class of such systems as discounted incomplete-information Markov games and show that two common pathologies, oscillation between competing conventions and drift across them, can both induce unstable learning and linear Bayesian regret. To obtain a well-posed target, we introduce the Heterogeneous Quantal Response Equilibrium (HQRE), an entropy-regularized equilibrium concept with agent- and state-dependent temperatures. Under a monotonicity condition, HQRE is unique, admits linearly convergent mirror updates, and yields bounded Bayesian regret; the same condition yields rollout-measurable stability diagnostics. We instantiate this objective in two algorithms: DICE-PC, which coordinates frozen models through prompt-control actions, and DICE-FT, which performs parameter-efficient mirror fine-tuning. Across eleven benchmarks in four domains, DICE improves accuracy-cost trade-offs over strong within-class baselines; on reasoning and planning tasks, DICE-PC improves by 4.3 percentage points on average and DICE-FT by 8.5 points.

Yi Xie, Zhanke Zhou, Chentao Cao +2

Department of Electrical & Computer Engineering University of Arizona Tucson, AZ 85721-0104, USA · Department of Computer Science Hong Kong Baptist University Kowloon Tong, Hong Kong SAR

Multi-Agent Coordination Game Theory Mirror Descent Multi-Agent LLMs

Jun 5, 2026cs.MA

GRPO Does Not Close the Multi-Agent Coordination Gap

We measure how well current large language models coordinate as multiple agents sharing a common resource, using the dining philosophers problem as a clean test bed. Across 630 episodes spanning seven models and three philosopher counts, four frontier closed-source systems reach mean reward 0.45 to 0.87 and Mistral-Small 24B reaches 0.83 to 0.99, while Qwen3-14B reaches 0.13 to 0.35. We then ask whether group relative policy optimization (GRPO) on rollouts from the task itself can close the gap and find that it cannot: a Welch's t-test on per-episode reward at five philosophers gives p = 0.66 and a Hedges' g of -0.11, with no statistically significant change at ten or fifteen philosophers either. Two further observations qualify the result. The training reward of both 8B and 14B runs peaked at step nine and then declined, so the default saved checkpoint at step 15 is strictly worse than several earlier ones. The four-term reward we use admits a degenerate maximum at zero actions, which DeepSeek-R1-Distill-Qwen-7B and Mistral-Small 24B at five philosophers both inhabit, with mean reward 1.0 and 0.83 respectively at zero meals. The bottleneck for an open-weight 14B model on multi-agent coordination is not training compute but training methodology: reward shaping that does not collapse to a no-action maximum, checkpoint discipline that does not depend on the final step, and curriculum across problem scales.

Najmul Hasan, Prashanth BusiReddyGari

Department of Mathematics and Computer Science, University of North Carolina at Pembroke, Pembroke, NC, USA

Multi-Agent System Optimization Multi-Agent Coordination Group Relative Policy Optimization Multi-Agent LLMs

Jun 5, 2026cs.CL

Representational Similarity and Model Behavior in Multi-Agent Interaction

Researchers have shown that neural similarity among humans predicts social closeness and cooperative success, whereas innovation often emerges from interactions among dissimilar individuals. We investigate whether these principles extend to artificial intelligence by examining interactions between large language models. In our experiments, 276 model pairs interact across eight games spanning both cooperation and novelty. We find that pairs with more similar representation spaces achieve significantly higher cooperation but exhibit reduced novelty and creativity. The effects of representational similarity on cooperation and novelty remain robust even after controlling for other factors such as performance disparity and model size. We also find that similarity in the early layers consistently shows the strongest association with cooperation and novelty, compared to the middle and later layers. This suggests that a central factor underlying these patterns could be the extent to which the two models share lexical and semantic grounding. Overall, representational similarity can be an important consideration in multi-agent system design.

Yujin Potter, Seun Eisape, Shiyang Lai +6

University of California, Berkeley · The University of Chicago, Knowledge Lab · Santa Fe Institute +2

Representational Similarity Analysis Multi-Agent Collaboration Multi-Agent LLMs Representation Alignment

Jun 5, 2026cs.MA

Modeling U.S. Attitudes Toward China via an Event-Steered Multi-Agent Simulator

Understanding the dynamic evolution of opinions, such as U.S. public attitudes toward China, is essential for assessing geopolitical risks. However, existing LLM-based multiagent simulators predominantly rely on static rules and fixed datasets, limiting their ability to capture the dynamic, event-driven nature of macro-level opinion shifts in real-world settings. To address this limitation, we propose an Event-Steered Multi-Agent Simulator (ES-MAS), in which significant events and daily news continuously drive opinion evolution through dynamic interactions among agents. We first construct the China-U.S. Relation Evolution (CURE) dataset, covering 20 quarters from 2021 to 2025, including 258 major events and over 14,000 daily news articles, and providing a comprehensive temporal foundation for modeling opinion dynamics. Building upon the CURE dataset, we propose a Dual-Stream Data Integration Engine (DSDIE) that aligns simulations with historical timelines via macro-level events while enabling personalized information exposure based on individual agent profiles and contextual signals. Furthermore, we design a News-Driven Dynamic Interaction (NDDI) module, which adaptively groups agents with shared news interests into localized interaction contexts, facilitating bottom-up consensus formation while mitigating the risk of isolated information cocoons. Experimental results on the CURE dataset demonstrate that ES-MAS substantially outperforms existing simulators in reproducing real-world historical trends, offering a scalable and effective framework for modeling dynamic opinion evolution.

Chenxu Zhu, Hantao Yao, Wu Liu +2

University of Science and Technology of China (USTC), Hefei 230026, China · People.cn, Beijing, China

Opinion Dynamics Human Behavior Simulation Multi-Agent LLMs

Jun 5, 2026cs.AI

AdMem: Advanced Memory for Task-solving Agents

Large Language Models (LLMs) show promise as tool-using agents but remain limited in long-horizon tasks that require remembering, organizing, and reusing knowledge. Prior memory approaches aim to resolve the situation, but mainly focus on storing factual information. Recent work on procedural memory improves task reuse, yet often reduces to replaying past successes without addressing failure cases or online scalability. We introduce a unified and automatic memory framework that integrates semantic, episodic, and procedural memory in a bi-level design combining short-term and long-term stores. A multi-agent architecture with actor, memory, and critic agents enables automatic memory generation, reward annotation, and adaptive retrieval. Long-term memory is managed through reward-based evaluation, merging, and pruning, ensuring scalability and continual improvement. Experiments across various environments show that our approach improves robustness and success on long multi-turn tasks compared to existing baselines. This work highlights the importance of comprehensive, adaptive memory for advancing LLM-based agents.

Runzhe Wang, Huilin Lu, Shengjie Liu +2

Princeton University · Amazon · Arm

Continual Learning for LLM Agents LLM Agent Memory Persistent Memory for Language Models Long-Horizon Agent Tasks Multi-Agent LLMs Agent Memory Management+1

Jun 4, 2026cs.CL

CAF-Gen: A Multi-Agent System for Enriching Argumentation Structures

Formalizing complex reasoning from natural text is one of the central challenges in computational linguistics. It requires systems to understand not just keywords but also the context and complex reasoning embedded in a text. Current Argument Mining (AM) techniques identify basic claims and premises, yet they often struggle to capture the richer structural information required by advanced schemas such as the Carneades Argumentation Framework (CAF), which incorporates features such as premise types, proof standards, and argument schemes. We address this limitation by introducing CAF-Gen, an automated multi-agent framework designed to enrich shallow argument structures into CAF-compliant argument models. By employing an iterative Creator-Reviewer pipeline, a creator agent's output is validated by a critical agent to ensure structural integrity. This multi-agent collaboration is crucial for mitigating the structural instability typical of single-pass generative models. Our experiments demonstrate that the iterative feedback loop improves the quality of the resulting data and achieves strong alignment with the original annotations, while producing structurally richer models. Our findings show that the multi-agent system can overcome the limitations of single-pass generation, providing a robust methodology for the automated modeling of formal argumentation.

Jakub Bąba, Jarosław A. Chudziak

Faculty of Electronics and Information Technology, Warsaw University of Technology, Poland

Argument Mining Computational Argumentation Multi-Agent LLMs

Jun 4, 2026cs.AI

MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery

Large language model (LLM) agents are increasingly applied to long-horizon tasks such as scientific discovery and machine learning engineering (MLE), where sustained self-evolution becomes a key capability. However, existing MLE agents suffer from inter-branch information isolation, memoryless search, and lack of hierarchical control, which together hinder long-horizon optimization. We present MLEvolve, an LLM-based self-evolving multi-agent framework for end-to-end machine learning algorithm discovery. By extending tree search to Progressive MCGS, MLEvolve enables cross-branch information flow through graph-based reference edges and gradually shifts the search from broad exploration to focused exploitation with an entropy-inspired progressive schedule. To allow the agent to evolve with accumulated experience, we introduce Retrospective Memory, which combines a cold-start domain knowledge base with a dynamic global memory for task-specific experience retrieval and reuse. For stable long-horizon iteration, we further decouple strategic planning from code generation with adaptive coding modes. Evaluation on MLE-Bench shows that MLEvolve achieves state-of-the-art performance across multiple dimensions including average medal rate and valid submission rate under a 12-hour budget (half the standard runtime). Moreover, MLEvolve also outperforms specialized algorithm discovery methods including AlphaEvolve on mathematical algorithm optimization tasks, demonstrating strong cross-domain generalization. Our code is available at https://github.com/InternScience/MLEvolve.

Shangheng Du, Xiangchao Yan, Jinxin Shi +11

1Shanghai Artificial Intelligence Laboratory · 2East China Normal University

Automated Algorithm Discovery Multi-Agent LLMs Self-Evolving Agents Memory-Augmented Language Model Agents

Jun 3, 2026cs.AI

LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization

Long-horizon autoformalization of research mathematics fails not only at hard lemmas, but at scale: statements drift, dependencies tangle, context decays, and local repairs corrupt distant work. We present LeanMarathon, a multi-agent harness for reliable research-level Lean autoformalization. Its core abstraction is an evolving blueprint: a Lean file that serves simultaneously as formal proof skeleton, natural-language proof graph, and shared system of record. Four contract-scoped agents construct, audit, prove, and repair this blueprint. These agents are coordinated by a two-stage orchestrator that first stabilizes target fidelity through adversarial review and then discharges the proof directed acyclic graph (DAG) from its dynamic leaves upward in parallel CI-gated rounds. LeanMarathon turns one brittle multi-hour run into many local, recoverable, parallel transactions. We evaluate LeanMarathon on two recent research papers spanning four Erdős problems (#1051, #1196, #164, #1217). Across three autonomous runs, it formalizes all seven target theorems with no sorry, proving 258 lemmas and theorems. These results show that reliable AI co-mathematics requires not only stronger provers, but durable harnesses that preserve target fidelity across long mathematical developments. The code can be found at https://github.com/YuanheZ/LeanMarathon.

Yuanhe Zhang, Yuekai Sun, Taiji Suzuki +2

Department of Statistics, University of Warwick, UK · Center for Advanced Intelligence Project, RIKEN, Japan · Department of Statistics, University of Michigan, USA +3

Lean Theorem Proving Autoformalization Multi-Agent LLMs

Jun 3, 2026cs.SI

Towards Multi-Agent-Simulation-Based Community Note Evaluation

Community-based fact-checking that relies on cross-consensus is expanding rapidly on social media platforms. However, the delay and low-ratio of cross-consensus community fact-checks rated by human contributors remains a significant challenge. To address this, we first created ComRate, a large-scale dataset comprising 2.5 million community notes and over 209 million ratings sourced from

\mathbb{X}

. We then propose MultiCom, a persona-guided multi-agent rating framework for community note evaluation. MultiCom simulates diverse rater population by clustering contributors in a matrix-factorized rater space and prompting persona agents to generate structured assessments based on the official community notes rating schema. These agents output structured and explainable judgments, such as confidence, agreement signals and reasons. An out-of-fold calibrated aggregation algorithm combines features such as raw votes and diagnostic reason signals for reliable prediction. Extensive evaluations demonstrate that MultiCom outperforms alternative methods, achieving an average accuracy of 84.7% (balanced accuracy 68.3%, macro-F1 60.1%) on the evaluation set.

Changxi Wen, Shuning Zhang, Bohao Chu +5

1Tsinghua University, Beijing, China · University of Duisburg-Essen, Duisburg, Germany · University of Luxembourg, Luxembourg +1

Automated Fact-Checking LLM Agents Multi-Agent LLMs

Jun 2, 2026cs.GR

Agentic Large Language Models for Automated Structural Analysis of 3D Frame Systems

Large language models (LLMs) have emerged as powerful foundation models with strong reasoning capabilities across domains. Beyond reactive text generation, agentic LLMs enable autonomous workflow execution through modular task decomposition and coordinated tool use. In structural engineering, recent efforts have developed agentic LLMs for automated analysis of plane frames. However, their extension to 3D frames remains underexplored due to challenges in irregular geometric representation, topological consistency, and long-horizon reasoning. This paper proposes an agentic LLM framework for automated structural analysis of 3D frames from natural language inputs. Irregular 3D frames are represented by projection onto a 2D plan, where orthogonal gridlines define spatial coordinates and a matrix of number of stories encodes vertical extrusion of each grid cell. Building on this representation, the framework establishes a multi-agent pipeline: a problem analysis agent parses input into structured JSON; a floor decomposition agent derives the spatial layout of each floor; the 3D geometry is assembled by node, girder, slab, and column agents; support and load agents assign boundary and loading conditions, and code translation agents generate executable SAP2000 script. Evaluated on ten representative 3D frames, the proposed framework achieves an average accuracy of 90% across repeated trials, demonstrating consistent and reliable performance.

Ziheng Geng, Ian Franklin, Santiago Martinez +3

Department of Civil and Architectural Engineering, University of Miami, Coral Gables, FL 33146, USA · School of Architecture, University of Miami, Coral Gables, FL 33146, USA · HBC Engineering Company, Doral, FL 33178, USA +1

Structural Mechanics Multi-Agent LLMs

Jun 2, 2026cs.AI

TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning

Assessing the quality of time series (TS) data is fundamental yet inherently challenging due to the multifaceted nature of quality dimensions. Recently, large language models (LLMs) have emerged as a promising paradigm for TS quality assessment via pairwise comparison and per-dimension evaluation. However, existing approaches rely on manually predefined quality dimensions and purely text-based reasoning, leaving it unknown whether LLMs can identify truly relevant quality dimensions or perform grounded and quantitative quality comparisons. To investigate this, we construct TSQBench, a dedicated benchmark for evaluating LLMs on two progressive capabilities: (i) understanding and identifying relevant quality dimensions, and (ii) performing quality comparison under specific dimensions. Our analysis reveals that current LLMs consistently struggle with both dimension identification and evidence-grounded quality comparison. To address these limitations, we propose TSQAgent, a novel agentic reasoning framework for TS quality rating consisting of three collaborative roles: Perceiver for focused dimension selection, Inspector for dimension-wise quantitative analysis, and Adjudicator that aggregates and refines the final judgment. In particular, we introduce an agentic reasoning strategy that instills the ability to identify and prioritize the most relevant quality dimensions, and further propose an agent workflow equipped with external analytical tools to enable precise quantitative comparisons over selected dimensions. Experiments on both the proposed benchmark and eleven real-world datasets demonstrate that our framework not only substantially improves LLMs' capabilities in quality understanding and quantitative comparison but also effectively translates these improvements into better quality-aware data selection, leading to enhanced downstream performance and data efficiency.

Shunyu Wu, Dan Li, Haozheng Ye +6

Sun Yat-sen University · China University of Mining Technology · University of Science and Technology of China +2

Agentic Reasoning Multi-Agent LLMs

Jun 2, 2026cs.AI

Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation

LLM-based multi-agent simulation offers a promising way to study social interaction, deliberation, and collective opinion dynamics. However, many existing dialogue simulation frameworks represent interaction mainly as observable turn exchange or aggregated outputs, leaving the internal evaluative processes behind silence, speaking intention, and public expression difficult to examine. We introduce TBS (Think-Before-Speak), an interval-based multi-agent simulation framework that separates agents' private reasoning from public utterance generation. At each interval, all agents update structured internal states based on the shared dialogue history and their own memory. These states include dissonance-related appraisal, perceived opinion climate, perceived isolation risk, response strategy, and willingness to speak. The orchestrator then resolves competing speaking intentions and commits one utterance to the public dialogue, allowing internal evaluation and public interaction to co-evolve over time. We evaluate TBS in simulated town hall discussions on a climate-related policy issue. Results show that TBS produces coherent internal-state traces and that these traces vary systematically across turn-allocation, silence, and memory conditions. Dissonance-related appraisal increases agents' willingness to speak, whereas silence-pressure appraisal decreases it. Once speaking intention is formed, public expression is shaped mainly by turn-allocation rules. These findings suggest that TBS supports mechanism-sensitive social simulation by making the pathway from internal evaluation to public expression observable and analyzable.

Kaiqi Yang, Tai-Quan Peng, Sanguk Lee +1

Michigan State University East Lansing, MI, USA · Hankuk University of Foreign Studies Seoul, Republic of Korea

Human Behavior Simulation Multi-Agent Systems Large Language Model-Based Social Simulation Multi-Agent LLMs

Jun 2, 2026cs.LG

MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency

Mixture-of-Agents (MoA) systems improve reasoning accuracy by routing each query to multiple expert LLMs and aggregating their outputs. Efficiently executing this workload on limited GPU resources has bottlenecks. Skill-based routing creates skewed expert demand, and combining instruction-tuned LLMs with long-reasoning models results in extreme variability in generation lengths. Consequently, traditional scheduling strategies suffer from significant GPU idling and throughput collapse due to load imbalances. We present MOSAIC, a scheduling framework to accelerate MoA workloads. First, we formulate an Integer Linear Program (ILP) based scheduler that jointly optimizes expert placement and per-worker prompt assignment from offline-profiled costs, replicating reasoning experts across workers while pinning lightweight ones. Second, MOSAIC uses confidence-aware adaptive aggregation, leveraging inter-expert agreement to bypass the heavy final aggregator LLM for consensus queries. In our 4-GPU system, MOSAIC achieves up to 2.5x expert-stage, 4.23x aggregator-stage and 1.7~2.3x end-to-end speedups over the baseline scheduler, while matching accuracy within 0.1pp.

Saptarshi Mitra, Yifan Zhang, Rachid Karami +5

University of California, Irvine, USA · University of Southern California, Los Angeles, USA · Intel, USA

LLM Inference Efficiency Multi-Agent System Optimization LLM Inference Scheduling LLM Agent Workflow Optimization LLM Inference Serving Multi-Agent LLMs

Jun 1, 2026cs.MA

The Epi-LLM Framework: probing LLM behavioral priors through epidemiological agent-based models

Human behaviour during epidemics affects infectious disease dynamics, but quantifying this remains deeply challenging. Here we introduce the Epi-LLM framework: a novel integration of agent-based modelling, real-life epigames, and large language models (LLMs) in which a synthetic society of agents reasons and adapts dynamically over an outbreak contact network. Comparing synthetic agent behaviour against a no-intervention SEIR baseline and human participant data from the AUIB epigame study, we find that LLM agents across four different architectures reduced peak active infections, with quarantine compliance peaking at 58-65% on day six of the 15-day simulation. A binomial generalised linear model showed that perceived health severity was the strongest predictor of quarantine behaviour (

β= 0.33, p = 0.002

), yielding a pseudo-

R^2

of 0.055, comparable to the 0.072 observed in the human trial. LLM architecture is a key determinant of epidemic dynamics: low-variance architectures offer greater internal validity for testing behavioural rules, while high-variance models may better represent real-world decision-making. Geographic labels alone do not induce culturally differentiated behaviour; explicit attitudinal parameterisation is required. This proof-of-principle work lays the groundwork for deploying the Epi-LLM framework as a scalable, risk-free simulation environment for pandemic preparedness research.

Petra Ferencz, Ava Keeling, Tobias O'Keefe +4

Big Data Institute, Li Ka Shing Center for Health Information and Discovery, University of Oxford, Oxford, United Kingdom · Leverhulme Centre for Demographic Science, Nuffield Department of Population Health, University of Oxford, Oxford, United Kingdom · Pandemic Sciences Institute, Nuffield Department of Medicine, University of Oxford, Oxford, United Kingdom +3

Human Behavior Simulation LLM Agent Evaluation Agent-Based Modeling Multi-Agent LLMs

Jun 1, 2026cs.MA

RadioMaster: Multi-Agent System for Autonomous Radio Signal Generation

Translating user intents into physical radio signals represents the critical yet notoriously tedious final step in wireless prototyping, as it requires intricate knowledge of physical layer details and presents immense implementation challenges. Large Language Models (LLMs) and multi-agent systems have revolutionized conventional software engineering, raising the compelling question of whether they can resolve these formidable difficulties. However, our investigations reveal that current models experience significant limitations and fail to accomplish this task when applied to radio signal generation. This performance degradation primarily stems from severe domain ignorance and a fundamental insensitivity to physical hardware constraints. To bridge this gap, we introduce RadioMaster, a fully autonomous multi-agent framework designed to seamlessly translate user input into real-world wireless emissions. RadioMaster operates on three synergistic pillars: RadioWiki for domain-specific knowledge retrieval, RadioAgent for collaborative I/Q sample generation alongside hardware configuration, and RadioEmulator for closed-loop physical layer verification. Furthermore, we construct RadioBench, the first comprehensive benchmark tailored specifically for the radio signal generation domain. Extensive real-world evaluations demonstrate that RadioMaster significantly outperforms state-of-the-art (SOTA) baselines regarding configuration viability and signal fidelity.

Jiazhen Lei, Tianze Cao, Yuxin Sha +5

Wireless Communications Multi-Agent LLMs

Jun 1, 2026cs.LG

A Theoretical Framework for Self-Play Theorem Proving Algorithms

Self-play, a type of training algorithm that enables a model to self-improve, has recently shown promising empirical results in the context of formal theorem proving using Large Language Models (LLMs). (Dong & Ma, 2025) instantiate self-play with two cooperating agents: a prover, which proves theorems, and a conjecturer, which generates new theorems as a curriculum to the prover. In this paper, we provide a theoretical framework for understanding the self-improvement capabilities of self-play algorithms for theorem proving. First, we formalize the set of theorems as a graph, with nodes as theorems and edges between pairs of theorems with similar semantics. We introduce a set of primitive assumptions that characterize the guarantees of a trained prover and how a conjecturer can access the structure of the graph. Second, we show that if the underlying graph of theorems is well-connected, then a prover-conjecturer system, where the conjecturing algorithm is based on a reversible random walk, is sufficient to grow the set of proved theorems exponentially. Third, motivated by an issue encountered empirically by self-play algorithms, where the conjecturer tends to generate artificially complex and non-fundamental theorems, we propose a diversity measure for a training distribution of theorems generated by a conjecturer and an improved conjecturing algorithm that locally maximizes this diversity measure, by computing the diffusion similarity between neighboring theorems in the theorem graph. Finally, we describe a method to compute the diffusion similarity by using contrastive learning to embed nodes into Euclidean space and then computing the inner-product between embeddings.

Thomas Chen, Zhiyuan Li

Automated Theorem Proving Language Model Self-Improvement Multi-Agent LLMs