Multi-Agent LLM Systems

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

85 papers in the last four weeks, up 107% on the four weeks before. 0.8% of all new papers.

Jul 13Week of Sep 28

Latest papers 665

May 13, 2026cs.CL

CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution

LLM-based multi-agent systems have demonstrated strong performance across complex real-world tasks, such as software engineering, predictive modeling, and retrieval-augmented generation. Yet automating their configuration remains a structural challenge, as scores are available only at the system level, whereas the parameters governing agent behavior are local. We argue that optimizing these systems is fundamentally a credit-assignment problem. We therefore introduce CANTANTE, a framework that decomposes system-level rewards into per-agent update signals by contrasting rollouts of multiple joint configurations on the same query. We instantiate it for prompt optimization, treating agent prompts as learnable system parameters. We evaluate CANTANTE against GEPA and MIPROv2 on programming (MBPP), mathematical reasoning (GSM8K), and multi-hop question answering (HotpotQA). Across these benchmarks, CANTANTE achieves the best average rank among all evaluated optimizers and consistently outperforms unoptimized prompts. It improves over the strongest baseline by +18.9 percentage points on MBPP and +12.5 percentage points on GSM8K, while incurring a lower inference cost. It remains within one standard deviation of the strongest baseline on HotpotQA. Crucially, our credit correlation analysis confirms that the attributer produces meaningful per-agent signals rather than echoing the global system score.

Tom Zehle

University of Freiburg · ELLIS Institute Tübingen

Multi-Agent LLM Systems Multi-Agent System Optimization Large Language Model-Guided Optimization LLM Agent Workflow Optimization Prompt Optimization Multi-Agent Reinforcement Learning

May 13, 2026cs.MA

A Multi-Agent Orchestration Framework for Venture Capital Due Diligence

We present a fully automated multi-agent framework for corporate due diligence and market analysis in venture capital. The system runs on an event-driven orchestration architecture, combining Large Language Models (LLMs) with real-time web retrieval to synthesize unstructured data into structured investment intelligence. A central technical contribution is a programmatic extraction pipeline that reverse-engineers the frontend-to-backend communication of the Greek Business Registry (

Γ

.E.MH.), querying dynamic endpoints to retrieve official financial filings that are then parsed using a layout-aware OCR extractor. A structural fallback mechanism explicitly flags data absence rather than generating unverified figures, directly targeting hallucination in financial contexts. All workflow artifacts are publicly available to support replication.

Grigorios Alexandrou, Katerina Pramatari

Department of Management Science and Technology, Athens University ofMay Economics and Business (AUEB), Athens, Greece

Multi-Agent LLM Systems LLM Agent Orchestration Finance

May 13, 2026cs.LG

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy

LLM-based multi-agent pipelines flip from correct to incorrect answers under simulated peer disagreement at rates we term yield, a vulnerability widely attributed to RLHF-induced sycophancy. We test this attribution across four model families and find it largely wrong: pretrained base models exhibit the same substitution pattern as their Instruct variants, averaging higher yield than Instruct. Using activation patching, we localize the corruption to a narrow mid-layer window where attention carries the causal weight and MLP contribution is negligible; patching above this window restores 96% of the clean-to-pressured P(correct) gap. The attack surface decomposes into two independent factors (channel framing and consensus strength) whose interaction produces a 47.5 percentage-point yield gap at majority consensus, preserved across jury sizes

N \in \{4, 5, 6\}

. Two converging activation-space interventions show that pressure suppresses clean-reasoning features rather than activating a new sycophancy circuit. A single correctly-arguing dissenter reduces yield by 54-73 percentage points across all framings tested, whereas the strongest prompt-level defense fails on attack variants outside its design surface. Mitigations should target the mechanism, structured dissent at the pipeline level, rather than prompt-level defenses.

Adarsh Kumarappan, Ananya Mujoo

1California Institute of Technology · 2Evergreen Valley College

AI Agent Reliability Multi-Agent LLM Systems LLM Sycophancy Adversarial Attacks on LLMs Multi-Agent Consensus Causal Interventions in Language Models

May 13, 2026cs.LG

Reinforced Collaboration in Multi-Agent Flow Networks

Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by different agents. However, their performance is often hindered by error propagation, arising from suboptimal workflow design or inaccurate agent outputs, which can propagate through the agent collaboration process and degrade final results. To address the challenges, we present MANGO (Multi-Agent Network Gradient Optimization), a data-driven framework that organizes and refines agent collaboration via a flow network constructed from past successful workflows. MANGO integrates reinforcement learning and textual gradients to jointly optimize workflow paths and agent behaviors, while a skipping mechanism prevents redundant updates to well-optimized agents for improving efficiency. Extensive experiments on seven benchmarks show that MANGO achieves up to 12.8% performance improvement over state-of-the-art baselines, enhances efficiency by 47.4%, and generalizes effectively to unseen domains. Our code and datasets are publicly available at https://github.com/openJiuwen-ai/agent-store/tree/main/community/mango.

Zheng Wang, Yuang Liu, Yangkai Ding

Huawei Technologies Co., Ltd.

Multi-Agent LLM Systems Multi-Agent Collaboration Multi-Agent Systems RL for LLM Agents

May 12, 2026cs.AI

CHAL: Council of Hierarchical Agentic Language

Multi-agent debate has emerged as a promising approach for improving LLM reasoning on ground-truth tasks, yet current methodologies face certain structural limitations: debate tends to induce a martingale over belief trajectories, majority voting accounts for most observed gains, and LLMs exhibit confidence escalation rather than calibration across rounds. We argue that the genuine value of debate, and dialectic systems as a whole, lies not in ground-truth tasks but in defeasible domains, where every position can in principle be defeated by better reasoning. We present the Council of Hierarchical Agentic Language (CHAL), a multi-agent dialectic framework that treats defeasible argumentation as an engine for belief optimization. Each agent maintains a CHAL Belief Schema (CBS), a graph-structured belief representation with a Bayesian-inspired architecture, that facilitates belief revision through a gradient-informed dynamic mechanism by leveraging the strength of the belief's thesis as a differentiable objective. Meta-cognitive value systems spanning epistemology, logic, and ethics are elevated to configurable hyperparameters governing agent reasoning and adjudication outcomes. We provide a series of ablation experiments that demonstrate systematic and interpretable effects: the adjudicator's value system determines the debate's overall trajectories in latent belief space, council diversity refines beliefs for all participants, and the framework generalizes across broad fields. CHAL is, to our knowledge, the first framework to treat multi-agent debate as structured belief optimization over defeasible domains. Further, the auditable belief artifacts it produces establish the foundation for dedicated evaluation suites for defeasible argumentation, with broader implications for building AI systems whose reasoning and value commitments are transparent, aligned, and subject to human oversight.

Tommaso Giovannelli, Griffin D. Kent

Belief Revision Multi-Agent LLM Systems Multi-Agent Debate Computational Argumentation

May 12, 2026cs.AI

ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows

Table processing-including cleaning, transformation, augmentation, and matching-is a foundational yet error-prone stage in real-world data pipelines. While recent LLM-based approaches show promise for automating such tasks, they often struggle in practice due to ambiguous instructions, complex task structures, and the lack of structured feedback, resulting in syntactically correct but semantically flawed code. To address these challenges, we propose ProfiliTable, an autonomous multi-agent framework centered on dynamic profiling, which constructs and iteratively refines a unified execution context through interactive exploration, knowledge-augmented synthesis, and feedback-driven refinement. ProfiliTable integrates (i) a Profiler that performs ReAct-style data exploration to build semantic understanding, (ii) a Generator that retrieves curated operators to synthesize task-aware code, and (iii) an Evaluator-Summarizer loop that injects execution scores and diagnostic insights to enable closed-loop refinement. Extensive experiments on a diverse benchmark covering 18 tabular task types demonstrate that ProfiliTable consistently outperforms strong baselines, particularly in complex multi-step scenarios. These results highlight the critical role of dynamic profiling in reliably translating ambiguous user intents into robust and governance-compliant table transformations.

Wei Liu, Yang Gu, Xi Yan +5

School of Software & Microelectronics, Peking University Beijing, China · Center for Machine Learning Research, Peking University Beijing, China Zhongguancun Academy Beijing, China

Multi-Agent LLM Systems Agentic Workflows LLM-Based Program Synthesis

May 12, 2026cs.SE

Iterative Audit Convergence in LLM-Managed Multi-Agent Systems: A Case Study in Prompt-Engineering Quality Assurance

Prompt specifications for multi-agent large language model (LLM) systems carry data contracts and integration logic across interdependent files but are rarely subjected to structured-inspection rigor. We report a single-system case study of iterative, agent-driven auditing applied to AEGIS (Autonomous Engineering Governance and Intelligence System), a seven-lane production pipeline whose 7152-line specification surface was audited across nine rounds, surfacing 51 consistency defects (per-round counts of 15, 8, 12, 2, 8, 1, 4, 1, 0). We present a seven-category post hoc taxonomy with explicit coding rules, non-monotonic convergence consistent with cascading edits and audit-scope expansion, and a locked audit protocol. We further report two partial replications on a public synthetic mini-specification: a cross-LLM panel of four frontier vendors (OpenAI, Anthropic, Google, xAI; 12 traces; multi-vendor union detects all five seeded defects) and an inter-rater reliability check on a stratified subsample (Cohen's

κ

= 0.80 on category, 0.46 on severity). The full reproducibility bundle accompanies the submission.

Elias Calboreanu

Swift AI Lab, The Swift Group, LLC, Reston, VA 20190, USA

Multi-Agent LLM Systems AI Agent Auditing LLM Auditing

May 12, 2026cs.AI

No Action Without a NOD: A Heterogeneous Multi-Agent Architecture for Reliable Service Agents

Large language model (LLM) agents have increasingly advanced service applications, such as booking flight tickets. However, these service agents suffer from unreliability in long-horizon tasks, as they often produce policy violations, tool hallucinations, and misaligned actions, which greatly impedes their real-world deployment. To address these challenges, we propose NOD (Navigator-Operator-Director), a heterogeneous multi-agent architecture for service agents. Instead of maintaining task state implicitly in dialogue context as in prior work, we externalize a structured Global State to enable explicit task state tracking and consistent decision-making by the Navigator. Besides, we introduce selective external oversight before critical actions, allowing an independent Director agent to verify execution and intervene when necessary. As such, NOD effectively mitigates error propagation and unsafe behavior in long-horizon tasks. Experiments on

τ^2

-Bench demonstrate that NOD achieves higher task success rates and critical action precision over baselines. More importantly, NOD improves the reliability of service agents by reducing policy violations, tool hallucinations, and user-intent misalignment.

Zixu Yang, Hang Zheng, Nan Jiang +5

1X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · 2Shanghai Innovation Institution, Shanghai, China · 3Jiangsu Key Lab of Language Computing, Suzhou, China

AI Agent Reliability Multi-Agent LLM Systems Tool-Using Agents LLM Agent Safety Long-Horizon LLM Agents LLM Agent Reliability

May 12, 2026cs.AI

Attributing Emergence in Million-Agent Systems

Large language models (LLMs) can simulate human-like reasoning and decision-making in individual agents. LLM-powered multi-agent systems (MAS) combine such agents to simulate population-scale social phenomena such as polarization, information cascades, and market panics. Such studies require attributing macro emergence to individual agents, but existing axiomatic methods scale combinatorially in

N

and have been confined to

N \lesssim 10^3

, while the phenomena they explain occur at

N \geq 10^6

. We address this gap by adapting Aumann--Shapley path-integral attribution to LLM-powered MAS at million-agent scale; the resulting method satisfies all four axioms, runs three to five orders of magnitude faster than sampled Shapley on the same hardware, and extends feasible axiomatic attribution by over three orders of magnitude (a

1670\times

jump). We use this method to test the scale gap empirically: across 14 days of public Bluesky data (

1{,}671{,}587

active users, five topics), we compute the attribution at both full scale and the visibility-biased

N = 10^2

convenience sample used by small-scale studies, and the two disagree structurally. At full scale the long tail and middle tier jointly carry the majority; the biased small panel shifts about twice that share onto the upper follower tiers (

48\%

versus

24\%

). We then prove that the disagreement cannot in general be reduced by post-hoc rescaling: an Attribution Scaling Bias theorem shows that a reconciling global rescaling factor exists exactly when the macro indicator is linear over agents, and our nonlinear indicators give residuals of

0.10

--

0.98

. For such nonlinear indicators, full-scale attribution is therefore a requirement rather than a methodological choice.

Ling Tang, Jilin Mei, Qian Chen +6

Shanghai Artificial Intelligence Laboratory · Fudan University · Tongji University +1

Multi-Agent LLM Systems Computational Social Science Shapley Value Attribution Large Language Model-Based Social Simulation Emergent Behavior in Multi-Agent Systems

May 12, 2026cs.AI

LLM-X: A Scalable Negotiation-Oriented Exchange for Communication Among Personal LLM Agents

We propose a personal-LLM exchange (LLM-X), a scalable negotiation-oriented environment that enables direct, structured communication across populations of personal agents (LLMs), each representing an individual user. Unlike existing tool-centric protocols that focus on agent-API interaction, LLM-X introduces a message bus and routing substrate for LLM-to-LLM coordination with guarantees around schema validity and policy enforcement. We contribute: (1) an architecture for LLM-X comprising federated gateways, topic-based routing, and policy enforcement; (2) a typed message protocol supporting capability negotiation and contract-net-style coordination; and (3) the first empirical evaluation of LLM-based multi-agent negotiation at scale. Experiments span 5, 9, and 12 agents, under distinct negotiation policies (Low, Medium, High), and across both short-run (minutes) and long-run (2h, 12h) load conditions. Results highlight clear policy-performance trade-offs: stricter policies improve robustness and fairness but increase latencies and message volume. Extended runs confirm that LLM-X remains stable under sustained load, with bounded latency drift.

Giuliano Lorenzoni, Paulo Alencar, Donald Cowan

University of Waterloo · University of Waterloo Waterloo, ON, Canada

Multi-Agent LLM Systems Multi-Agent Coordination Multi-Agent Negotiation Automated Negotiation Multi-Agent Communication

May 11, 2026physics.soc-ph

Strategic Coercion Within Alliances: The Greenland Sovereignty Game as an AI Stress Test

What happens when the strongest alliance member pressures a weaker member over territory and strategic control? We examine the Greenland sovereignty crisis as a stress test for LLM geopolitics, centered on the 2019-2026 U.S. push to acquire Greenland from the Kingdom of Denmark. The crisis nests two collective-action problems: Arctic strategic control and whether NATO can enforce alliance norms against the dominant member. We develop three games (asymmetric coercion; a NATO assurance game with a critical-mass tipping point; a triadic extensive-form game with social preferences) and test them with a multi-agent simulation in which eight frontier LLMs play six geopolitical roles (United States, Denmark, Greenland, NATO, Russia, Canada) across 3,604 completed games and 108,120 action observations. Using inverse game theory, we recover each model's structural utility parameters (alpha, beta, gamma, delta, eta) for material self-interest, reciprocity, inequality aversion, norm respect, and commitment consistency. Three findings stand out. First, all eight models become more escalatory under coercion framing (four-action escalation rises from 10.7% to 28.6%). Second, Chinese-origin models show systematically different power-weight profiles from Western-origin models when playing the U.S. role. Third, peaceful US acquisition emerges in only 1.9% of clean games and only 3 of 8 frontier models ever achieve it, most prominently DeepSeek V3.2, which executes a stable five-round playbook through the metropole. Prompts emphasizing jus cogens and self-determination reduce escalation back near baseline in the English-only confirmatory sample; multilingual contrasts are reported as exploratory sensitivity checks. We position this as a structural benchmark for LLM geopolitical behavior, complementing action-frequency benchmarks.

Rommin Adl, Peyton Williams

Grinnell College

Multi-Agent LLM Systems AI Agent Benchmarks

May 11, 2026cs.AI

EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales

We argue that multi-agent test-time evolution is not single-agent evolution replicated N times. A single-agent learner can only evolve its own context and memory. A multi-agent system additionally evolves who collaborates, how they collaborate, and how knowledge flows across the population. These components have no single-agent counterpart and can produce phenomena such as emergent specialization. Yet prior test-time methods either confine experiences to individual agents, forfeiting cross-agent learning, or broadcast symmetrically to all agents, erasing the specialization that makes collaboration valuable. We present EVOCHAMBER, a training-free framework that instantiates test-time evolution at three levels over a coevolving agent pool. At its core is CODREAM (Collaborative Dreaming), a post-task protocol triggered on team failure or disagreement, in which agents collaboratively reflect, distill insights, and route them asymmetrically from strong to weak agents on the failed niche, preserving specialization while filling knowledge gaps. Team-level operators assemble niche-conditioned teams and select collaboration structures online. Population-level lifecycle operators fork, merge, prune, and seed agents under performance pressure. On three heterogeneous task streams with Qwen3-8B, EVOCHAMBER reaches 63.9% on competition math, 75.7% on code, and 87.1% on multi-domain reasoning, outperforming the best baseline by 32% relative on math and confirming asymmetric cross-agent transfer as the primary driver in ablation. Starting from several identically initialized agents, four to five stable niche specialists spontaneously emerge, a structural signature of multi-agent evolution that no single-agent learner can express. See our code at: https://github.com/Mercury7353/EvoChamber

Yaolun Zhang, Tianyi Xu, Shengyu Dai +3

1Oregon State University · 5AG2AI, Inc. · University of Wisconsin–Madison +2

Multi-Agent LLM Systems Multi-Agent Collaboration Self-Evolving Agents Emergent Behavior in Multi-Agent Systems

May 11, 2026cs.AI

NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation

LLM-powered multi-agent systems can now automate the full research pipeline from ideation to paper writing, but a fundamental question remains: automation for whom? Researchers operate under different resource configurations, hold different methodological preferences, and target different output formats. A system that produces uniform outputs regardless of these differences will systematically under-serve every individual user, making personalization a precondition for research automation to be genuinely usable. However, achieving it requires three capabilities that current systems lack: accumulating reusable procedural knowledge across projects, retaining user-specific experience across sessions, and internalizing implicit preferences that resist explicit formalization. We propose NanoResearch, a multi-agent framework that addresses these gaps through tri-level co-evolution. A skill bank distills recurring operations into compact procedural rules reusable across projects. A memory module maintains user- and project-specific experience that grounds planning decisions in each user's research history. A label-free policy learning converts free-form feedback into persistent parameter updates of the planner, reshaping subsequent coordination. These three layers co-evolve: reliable skills produce richer memory, richer memory informs better planning, and preference internalization continuously realigns the loop to each user. Extensive experiments demonstrate that NanoResearch delivers substantial gains over state-of-the-art AI research systems, and progressively refines itself to produce better research at lower cost over successive cycles.

Jinhang Xu, Qiyuan Zhu, Yujun Wu +11

1Shanghai Artificial Intelligence Laboratory · 2The Hong Kong University of Science and Technology · 3Peking University +4

Multi-Agent LLM Systems LLM Agent Skill Learning LLM Agents Preference Learning Memory-Augmented Agents Autonomous Research Agents

May 11, 2026cs.AI

PRISM: Generation-Time Detection and Mitigation of Secret Leakage in Multi-Agent LLM Pipelines

Multi-agent LLM systems introduce a security risk in which sensitive information accessed by one agent can propagate through shared context and reappear in downstream outputs, even without explicit adversarial intent. We formalise this phenomenon as propagation amplification, where leakage risk increases across agent boundaries as sensitive content is repeatedly exposed to downstream generators. Existing defences, including prompt-based safeguards, static pattern matching, and LLM-as-judge filtering, are not designed for this setting: they either operate after generation, rely primarily on surface-form patterns, or add substantial latency without modelling the generation process itself. To resolve these issues, we propose PRISM, a real-time defence that treats credential leakage as a sequential risk accumulation problem during generation. At each decoding step, PRISM combines 16 signals spanning lexical, structural, information-theoretic, behavioural, and contextual features into a calibrated risk score, enabling per-token intervention through green, yellow, and red risk zones. Our central observation is that credential reproduction is often preceded by a measurable shift in generation dynamics, characterised by entropy collapse and increasing logit concentration. When combined with text-structural cues such as identifier-pattern detection, these temporal signals provide an early warning of leakage before a secret is fully reconstructed. Across a 2,000-task adversarial benchmark covering 13 attack categories and three pressure levels in a heterogeneous four-agent pipeline, PRISM achieves F1 = 0.832 with precision = 1.000 and recall = 0.712, while producing no observed leakage on our benchmark (0.0% task-level leak rate) and preserving output utility of 0.893. It substantially outperforms the strongest baseline, Span Tagger, which achieves F1 = 0.719 with a 15.0% task-level leak rate.

Riya Tapwal, Abhishek Kumar, Carsten Maple

School of Computing and Electrical Engineering · Indian Institute of Technology, Mandi (IIT) · The Alan Turing Institute, London +1

Data Leakage Multi-Agent LLM Systems Adversarial Attacks on LLMs LLM Agent Security Privacy Leakage in Language Models

May 11, 2026cond-mat.stat-mech

Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physics

We investigate the emergent collective dynamics of LLM-based multi-agent systems on a 2D square lattice and present a model-agnostic statistical-physics method to disentangle social conformity from intrinsic bias, compute critical exponents, and probe the collective behavior and possible phase transitions of multi-agent systems. In our framework, each node of an

L\!\times\!L

lattice hosts an identical LLM agent holding a binary state (

+1

/

-1

, mapped to yes/no) and updating it by querying the model conditioned on the four nearest-neighbor states. The sampler temperature

T

serves as the sole control parameter. Across three open-weight models (llama3.1:8b, phi4-mini:3.8b, mistral:7b), we measure magnetization and susceptibility under a global-flip protocol designed to probe

\mathbb{Z}_2

symmetry. All models display temperature-driven order-disorder crossovers and susceptibility peaks; finite-size scaling on even-

L

lattices yields effective exponents

γ/ν

whose values are model-dependent, close to but incompatible with the 2D Ising universality class (

γ/ν=7/4

). Our method enables the extraction of effective

β

-weighted couplings

\tilde{J}(T)

and fields

\tilde{h}(T)

, which serve as a measure of social conformity and intrinsic bias. In the models we analyzed, we found that collective alignment is dominated by an intrinsic bias (

\tilde{h}\gg\tilde{J}

) rather than by cooperative neighbor coupling, producing field-driven crossovers instead of genuine phase transitions. These effective parameters vary qualitatively across models, providing compact collective-behavior fingerprints for LLM agents and a quantitative diagnostic for the reliability of multi-agent consensus and collective alignment.

Cristiano De Nobili

Critiqality, Milan, Italy

Multi-Agent LLM Systems Multi-Agent Coordination Opinion Dynamics Social Bias in Language Models Phase Transitions Multi-Agent Systems+1

May 11, 2026cs.MA

Safe Multi-Agent Behavior Must Be Maintained, Not Merely Asserted: Constraint Drift in LLM-Based Multi-Agent Systems

Modern LLM based agents are no longer passive text generators. They read repositories, call tools, browse the web, execute code, maintain memory, communicate with other agents, and act through long horizon workflows. This shift moves the unit of safety. A system may produce a compliant final answer while leaking private information through an internal message, delegating authority beyond its original scope, calling an external tool with sensitive context, or losing the evidence needed to reconstruct why an action was allowed. We argue that many emerging failures in LLM-based multi-agent systems share a common structure: safety critical constraints do not remain operative throughout the trajectory. We call this phenomenon constraint drift: the loss, distortion, weakening, or relaxation of constraints as they pass through memory, delegation, communication, tool use, audit, and optimization. The position taken here is that safe multi-agent behavior must be maintained, not merely asserted. Prompts, guardrails, tool schemas, access control, and final output checks are necessary, but they are insufficient unless constraints remain fresh, inherited, enforceable, and auditable across execution. We propose Constraint State Governance as a research paradigm for LLM-based multi-agent systems. In this paradigm, safety-critical constraints are maintained as explicit execution state, while constraint-native reinforcement learning improves utility only within maintained safety boundaries. The goal is not to freeze agentic systems under rigid rules, but to make safety operational across the trajectories through which modern agents actually act.

Tianxiao Li, Yixing Ma, Haiquan Wen +4

University of Liverpool, UK · University of Nottingham, UK · University of Tokyo, Japan +1

Multi-Agent LLM Systems AI Agent Governance LLM Agent Safety

May 11, 2026cs.AI

TMAS: Scaling Test-Time Compute via Multi-Agent Synergy

Test-time scaling has become an effective paradigm for improving the reasoning ability of large language models by allocating additional computation during inference. Recent structured approaches have further advanced this paradigm by organizing inference across multiple trajectories, refinement rounds, and verification-based feedback. However, existing structured test-time scaling methods either weakly coordinate parallel reasoning trajectories or rely on noisy historical information without explicitly deciding what should be retained and reused, limiting their ability to balance exploration and exploitation. In this work, we propose TMAS, a framework for scaling test-time compute via multi-agent synergy. TMAS organizes inference as a collaborative process among specialized agents, enabling structured information flow across agents, trajectories, and refinement iterations. To support effective cross-trajectory collaboration, TMAS introduces hierarchical memories: the experience bank reuses low-level reliable intermediate conclusions and local feedback, while the guideline bank records previously explored high-level strategies to steer subsequent rollouts away from redundant reasoning patterns. Furthermore, we design a hybrid reward reinforcement learning scheme tailored to TMAS, which jointly preserves basic reasoning capability, enhances experience utilization, and encourages exploration beyond previously attempted solution strategies. Extensive experiments on challenging reasoning benchmarks show that TMAS achieves stronger iterative scaling than existing test-time scaling baselines, with hybrid reward training further improving scaling effectiveness and stability across iterations. Code and data are available at https://github.com/IQuestLab/tmas.

George Wu, Nan Jing, Qing Yi +7

1IQuest Research · 2Beihang University

Multi-Agent LLM Systems RL for Language Model Reasoning Test-Time Scaling Memory-Augmented Language Model Agents

May 11, 2026cs.AI

AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks

Building effective clinical decision support systems requires the synthesis of complex heterogeneous multimodal data. Such modalities include temporal electronic health records data, medical images, radiology reports, and clinical notes. Large language model (LLM)-based agents have shown impressive performance in various healthcare tasks, especially those involving textual modalities. Considering the fragmentation of healthcare data across hospital systems, collaborative agent frameworks present a promising direction to mitigate data sharing challenges. However, the effectiveness of LLM agents for multimodal clinical risk prediction remains largely unexamined. In this work, we conduct a systematic evaluation of LLM-based agents for clinical prediction tasks using large-scale real-world data. We assess performance in unimodal and multimodal settings and quantify performance gaps between single agent and multi-agent systems. Our findings highlight that single agent frameworks outperform naive multi-agent systems, are better at handling multimodal data, and are better calibrated. This underscores a critical need for improving multi-agent collaboration to better handle heterogeneous inputs. By open-sourcing our code and evaluation framework, this work offers a new benchmark to support future developments relating to agentic systems in healthcare.

Baraa Al Jorf, Farah E. Shamout

New York University Abu Dhabi, UAE

Multi-Agent LLM Systems LLM Agent Evaluation AI Agent Benchmarks Multimodal Agents Clinical Risk Prediction

May 11, 2026cs.CL

NyayaAI: An AI-Powered Legal Assistant Using Multi-Agent Architecture and Retrieval-Augmented Generation

Legal information in India remains largely inaccessible due to the complexity of legal language and the sheer volume of legal documentation involved in research and case analysis. This paper presents NyayaAI, an AI-powered legal assistant that automates and simplifies legal workflows for lawyers, law students, and general users. The system combines Large Language Models with a Retrieval-Augmented Generation pipeline grounded in a curated Indian legal knowledge base comprising constitutional provisions, statutes, case laws, and judicial precedents. A multi-agent architecture orchestrated through the Mastra TypeScript framework coordinates a main agent with specialized sub-agents handling legal research, document summarization, case law retrieval, and drafting assistance. A compliance module validates all responses before delivery. Domain classification achieved 70% precision across test samples, with RAG retrieval precision at 74% and overall response accuracy at 72%, demonstrating that structured multi-agent LLM systems can meaningfully improve legal accessibility and workflow efficiency. The code\footnote{https://github.com/B97784/NyayaAI} is made publicly available for the benefit of the research community.

Deepanshu, Divi Saxena, Deepali Rana +2

School of Computer Science UPES, Dehradun, India

Multi-Agent LLM Systems Legal IR Agentic RAG Legal QA

May 11, 2026cs.AI

MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs

Self-evolving language-model agents must decide what to learn next and how to preserve what they have learned across iterations. Existing systems typically carry this cross-iteration knowledge as natural-language feedback, flat episodic memory, or implicit reinforcement signals, none of which cleanly supports a frozen weak backbone at inference time. This paper introduces MAGE (Multi-Agent Graph-guided Evolution), a framework that externalizes self-knowledge into a four-subgraph co-evolutionary knowledge graph. Its experience subgraph stores both teacher-written failure corrections and the learner's own past correct reasoning traces, which are retrieved as task-conditioned guidance for a frozen execution model. During evolution, the graph, a task-level search bandit, and a skill-level routing bandit are updated from the same reward stream, while the learner's backbone remains unchanged. We further provide structural analysis showing how append-only memory growth, bounded curriculum coverage, and task-filtered retrieval together support stable improvement of the retrieval substrate for frozen-learner evolution. Across nine benchmarks spanning mathematical reasoning, multi-hop and open-domain question answering, spatio-temporal analysis, financial numerical reasoning, medical multiple-choice, an open-world survival game, and web navigation, MAGE achieves strong performance against prompt-based frozen-backbone baselines. Ablations show that self-harvested success traces and teacher-written corrections are complementary, with success memories contributing most on reasoning-template-heavy tasks and corrective memories supporting harder composition and interaction settings.

Ruiyi Yang, Zechen Li, Hao Xue +2

University of New South Wales · The Hong Kong University of Science and Technology (Guangzhou) · Mohamed Bin Zayed University of Artificial Intelligence

Agent Memory Continual Learning for LLM Agents Multi-Agent LLM Systems Graph-Based Agent Memory Agent Memory Management Self-Evolving Agents

May 11, 2026cs.AI

STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoning

Compositional spatiotemporal reasoning often requires a system to invoke multiple heterogeneous specialists, such as geometric, temporal, topological, and trajectory agents. A central question is how such a system should route among specialists when execution does not simply succeed or fail, but fails in qualitatively different ways. Existing tool-augmented and multi-agent LLM systems typically leave this routing decision implicit in language generation, making recovery ad hoc, difficult to interpret, and hard to optimize. This paper presents STAR (Spatio-Temporal Agent Router), a failure-aware routing framework that externalizes inter-agent control as a state-conditioned transition policy over the current agent, task type, and typed execution status. At the center of STARis an agent routing matrix that combines expert-specified nominal routes with recovery transitions learned from execution traces. Because the matrix conditions on distinct failure states, the router can respond differently to malformed outputs, missing dependencies, and tool--query mismatches, rather than collapsing them into a generic retry signal. Specialists execute through a tool-grounded extract--compute--deposit protocol and write intermediate results to a shared blackboard for downstream fusion. Results prove that retaining unsuccessful traces during training enlarges the support of the routing policy on error states, enabling recovery transitions that success-only training cannot represent. Across three spatiotemporal benchmarks and eight backbone LLMs, STAR improves over multiple baselines with the clearest gains on queries whose execution deviates from the nominal routing path. Router-specific ablations and recovery analyses further show that typed failure-aware routing, rather than specialist composition alone, is a key factor for these improvements.

Ruiyi Yang, Lihuan Li, Hao Xue +1

University of New South Wales · The Hong Kong University of Science and Technology (Guangzhou)

Multi-Agent LLM Systems Spatiotemporal Reasoning LLM Agent Routing

May 11, 2026cs.AI

RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generation

Compared with individual agents, large language model based multi-agent systems have shown great capabilities consistently across diverse tasks, including code generation, mathematical reasoning, and planning, etc. Despite their impressive performance, the effectiveness and robustness of these systems heavily rely on their communication topology, which is often fixed or generated in a single step. This restricts fine-grained structural exploration and flexible composition, resulting in excessive token utilization on simple tasks while limiting capability on complicated tasks. To mitigate this challenge, we introduce RADAR, a redundancy-aware and query-adaptive generative framework that actively reduce communication overhead. Motivated by recent progress in conditional discrete graph diffusion models, we formulate communication topology design as a step-by-step generation process, guided by the effective size of the graph. Comprehensive experiments on six benchmarks demonstrate that RADAR consistently outperforms recent baselines, achieving higher accuracy, lower token consumption, and greater robustness across diverse scenarios. Our code and data are available at https://github.com/cszhangzhen/RADAR.

Zhen Zhang, Wanjing Zhou, Juncheng Li +3

National Key Laboratory for Novel Software Technology, Nanjing University, China · Zhejiang University · University of Oxford +1

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Communication

May 10, 2026cs.MA

CalBench: Evaluating Coordination-Privacy Trade-offs in Multi-Agent LLMs

Personal AI assistants are beginning to act as delegates with access to calendars, inboxes, and user preferences. Calendar scheduling makes the trust problem concrete: an assistant must coordinate with other assistants while deciding what to reveal about the person it represents. We introduce CalBench, a controlled benchmark for multi-agent calendar scheduling under private information. In each task,

N

agents manage separate private calendars and schedule a stream of

M

incoming meetings while minimizing disruption costs. Because no agent can inspect another agent's calendar, success requires language-mediated coordination rather than centralized planning. CalBench generates solvable scenarios with CP-SAT oracle solutions and decentralized non-LLM reference protocols, enabling evaluation of task success, excess cost, communication efficiency, burden fairness, and privacy leakage under matched information constraints. Across seven model families, we find that completion alone misses important failures: agents leave avoidable cost on the table, communication volume does not predict lower regret, and privacy-preserving silence can deprive teammates of cost information needed for fair burden allocation. CalBench provides a reproducible testbed for studying whether autonomous assistants can coordinate on behalf of users before deployment at scale.

Chelsea Zou, Yiheng Yao, Selena She +2

Stanford University

Multi-Agent LLM Systems Multi-Agent Coordination AI Agent Benchmarks Multi-Agent Systems

May 10, 2026cs.AI

UTS at PsyDefDetect: Multi-Agent Councils and Absence-Based Reasoning for Defense Mechanism Classification

This paper describes our system for classifying psychological defense mechanisms in emotional support dialogues using the Defense Mechanism Rating Scales (DMRS), placing second (F1 0.406) among 64 teams. A central insight is that defense mechanisms are defined by what is absent: missing affect, blocked cognition, denied reality. We encode this as an affect-cognition integration spectrum in prompt-level clinical rules, which account for the largest single gain (+11.4pp F1). Our architecture is a multi-phase deliberative council of Gemini 2.5 agents where class-specific advocates rate evidence strength rather than voting, achieving F1 0.382 with no fine-tuning - a top-5 result on its own. We find, however, that the council is confidently wrong about minority classes: 59-80% of stable minority predictions are incorrect, driven by a systematic "L7 attractor" in which emotional content defaults to the majority class. A targeted override ensemble from three fine-tuned Qwen3.5 models applies 16 overrides (+2.4pp), selected by a structured multi-agent system (builder, critic, regression guard) that produced a larger F1 gain in one iteration than 8 prior attempts combined.

Dima Galat, Marian-Andrei Rizoiu

University of Technology Sydney

Multi-Agent LLM Systems Mental Health Multi-Agent Reasoning

May 10, 2026cs.AI

Workspace Optimization: How to Train Your Agent

Modern agents built on frontier language models often cannot adapt their weights. What, then, remains trainable? We argue it is the agent's \emph{workspace}, the structured external substrate it reads, writes, and tests; we call its evolution workspace optimization. Workspace optimization targets hard multi-turn environments where a frontier model has strong priors but cannot solve the task in a single shot, so the agent must learn through interaction. We propose a principled way to evolve the workspace, mirroring the structure of weight-space training: artifacts in place of parameters, evidence in place of data, counterexamples in place of losses, and textual feedback in place of gradients. We instantiate the idea in DreamTeam, a multi-agent harness for ARC-AGI-3 whose roles build an executable world model, plan, hypothesize, probe, strategize, and route failures. On the current 25-game ARC-AGI-3 public set under the official scoring protocol and averaged over two independent runs, DreamTeam improves the SOTA protocol-matched agent's score from 36% to 38.4%, while using 31% fewer environment actions per game.

Elad Sarafian, Gal Kaplun, Ron Banner +2

NVIDIA · NVIDIA & Technion

Multi-Agent LLM Systems LLM Agent Self-Improvement LLM Agent Harnesses

May 10, 2026cs.CL

TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems

Multi-agent systems (MAS) have emerged as a promising paradigm for solving complex tasks. Recent work has explored self-evolving MAS that automatically optimize agent capabilities or communication topologies. However, existing methods either learn a topology that remains fixed at inference time or adapt only the topology or capability during inference. We empirically and theoretically show that effective test-time evolution requires jointly adapting both axes, but on different time scales: capabilities should update rapidly to handle emerging subtasks, while the topology should evolve more slowly to preserve coordination stability. We then introduce TacoMAS, a test-time co-evolution framework for dynamic MAS. TacoMAS formulates MAS inference as a task of online graph adaptation, where nodes represent agents with role-specific capabilities and edges define their communication topology. During inference, a fast capability loop updates agent expertise using trajectory-level feedback, while a slow meta-LLM-driven topology loop performs agents' birth-death operations on MAS, including edge edit, agent addition, and agent removal. We further show that this fast-slow design drives MAS evolution toward a task-conditioned stable equilibrium. Experiments on four benchmarks demonstrate that TacoMAS outperforms nearly 20 multi-agent baselines, achieving an average improvement of 13.3% over the strongest baseline. The codes are released at https://github.com/chenxu2-gif/TacoMAS-MultiAgent.

Chen Xu, Yicheng Hu, Ruizi Wang +4

1Carnegie Mellon University · University of Science and Technology of China · 3National University of Singapore +1

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Systems Multi-Agent Communication Self-Evolving Agents

May 9, 2026cs.MA

Robust Multi-Agent LLMs under Byzantine Faults

Large language model (LLM) agents increasingly collaborate over peer-to-peer networks to improve their reliability. However, these same interactions can also become a source of vulnerability, as unreliable or Byzantine agents may sway neighboring agents toward incorrect conclusions and degrade overall system performance. Existing methods rely on leader-based coordination or self-reported confidence, both of which are susceptible to adversarial manipulation. We study decentralized LLM multi-agent systems (LLM-MAS) and propose Self-Anchored Consensus (SAC), a fully decentralized iterative filter-and-refine protocol in which agents iteratively exchange responses, locally evaluate and filter unreliable messages, and refine their own outputs. We present

(F{+}1)

-robustness conditions for the communication graph that ensure honest agents preserve and propagate reliable information despite Byzantine influence. Experiments on mathematical and commonsense reasoning benchmarks show that SAC effectively suppresses Byzantine influence and consistently improves performance across diverse communication topologies, whereas prior methods degrade under adversarial conditions.

Haejoon Lee, Vincent-Daniel Yun, Dimitra Panagou +1

Department of Robotics, University of Michigan, Ann Arbor, USA · Thomas Lord Department of Computer Science, University of Southern California, USA

Multi-Agent LLM Systems Multi-Agent Coordination Multi-Agent Systems Multi-Agent Consensus Multi-Agent Reasoning Multi-Agent Communication

May 9, 2026cs.LG

Trustworthy AI: Ensuring Reliability and Accountability from Models to Agents

In this thesis, we develop algorithms with theoretical guarantees for ensuring reliability and accountability of Machine Learning (ML) systems. As ML systems evolve from predictive models to generative models and autonomous agents, the landscape of trustworthy AI has shifted. This thesis introduces tools grounded in information theory, optimization, and statistical learning to mitigate bias, reduce arbitrary decisions, ensure content provenance, and evaluate LLM-driven agents in autonomous settings. Towards mitigating bias and arbitrariness in traditional ML models, we introduce a kernel-based method to achieve multiaccuracy across complex subpopulations that traditional demographic categories may overlook. We also develop methods to address predictive multiplicity, where equally accurate models yield conflicting individual predictions. We ensure the accountability in generative AI through watermarking large language models (LLMs). We characterize the information-theoretic trade-off between watermark detection and text distortion and derive optimal watermarking strategies by leveraging optimal transport and coding theory. Empirical evaluations show our watermarks achieve a superior detection-quality tradeoff across language generation and coding tasks. Finally, we evaluate autonomous LLM agents in multi-agent environments through the first simulator of a fully LLM-driven supply chain. LLM agents offer significant performance gains, outperforming human teams and reducing costs by up to 67%, but also introduce systemic risks, including costly tail events.

Carol Xuan Long

John A. Paulson School Of Engineering And Applied Sciences, Harvard University, Cambridge, Massachusetts

Multi-Agent LLM Systems AI Accountability LLM Watermarking LLM Agent Reliability

May 9, 2026cs.LG

AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems

Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex tasks. However, manually designing optimal communication topologies is labor-intensive, while automated expansion methods often result in bloated structures with redundant agents, leading to excessive token consumption. To address this problem, we introduce \textbf{AgentSlimming}, a plug-and-play compression framework for graph-structured multi-agent workflows. Motivated by pruning and quantization in neural networks, AgentSlimming compresses workflows by first estimating the importance score of each agent with a hybrid mechanism, and then removes redundant agents or replaces them with low-cost ones, where each operation is validated using a baseline-anchored acceptance rule to prevent performance collapse. Experiments show that AgentSlimming reduces average token cost by up to 78.9% with negligible performance degradation, and sometimes even improves accuracy, achieving a strong Pareto-optimal trade-off between cost and quality. \textit{Our code is publicly available at https://github.com/CitrusYL/AgentSlimming

Yulang Chen, Haoxuan Peng, Jinyan Liu +3

1Shanghai Jiao Tong University · 2Nanjing University · 3The University of Sydney +2

Multi-Agent LLM Systems Multi-Agent System Optimization LLM Agent Workflow Optimization Token Efficiency Multi-Agent Systems

May 9, 2026cs.AI

EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems

Large language model (LLM)-based multi-agent systems have shown strong potential on complex tasks through agent specialization, tool use, and collaborative reasoning. However, most automated multi-agent system design methods still follow a one-shot paradigm: a workflow is optimized or selected before execution and then reused unchanged throughout the task. This static coordination strategy is ill-suited for long-horizon tasks whose subgoals, intermediate evidence, and information needs evolve over multiple execution stages. We propose EvoMAS, a framework for execution-time multi-agent workflow construction. EvoMAS formulates workflow construction as a meta-level sequential decision problem along a single task trajectory. At each stage, it constructs an explicit task state through a Planner-Evaluator-Updater pipeline and uses a learned Workflow Adapter to instantiate a stage-specific layered workflow from a fixed pool of candidate agents. The adapter is trained with policy gradients using sparse, verifiable terminal task success as the main supervision signal, while evaluator-based process reward is analyzed separately under very-hard sparse-reward settings. Experiments on GAIA, HLE, and DeepResearcher show that EvoMAS outperforms single-agent baselines and recent automated multi-agent workflow design methods. Our analyses further show that explicit task-state construction and learned workflow adaptation provide complementary benefits. Additional results indicate that process reward is most useful when terminal success is extremely sparse, and qualitative case studies illustrate that EvoMAS adapts agent coordination as the task state evolves.

Chengdong Xu, Kaiqiang Ke, Ziheng Liu +4

Sun Yat-Sen University · ShanghaiTech University · Zhejiang University +1

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Orchestration LLM Agent Workflow Optimization Long-Horizon LLM Agents RL for LLM Agents