# Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs

arXiv: https://arxiv.org/abs/2505.11556 · HTML: https://mlsanity.com/paper/2505.11556/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 18 of its 81 references that are in the map.
- First posted on arXiv 15 May 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 18 of 18)

- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration](https://mlsanity.com/paper/2310.02170/) (2023)
- [Building Cooperative Embodied Agents Modularly with Large Language Models](https://mlsanity.com/paper/2307.02485/) (2023)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [Emergent autonomous scientific research capabilities of large language models](https://mlsanity.com/paper/2304.05332/) (2023)
- [SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement](https://mlsanity.com/paper/2410.20285/) (2024)
- [Understanding and Improving Information Transfer in Multi-Task Learning](https://mlsanity.com/paper/2005.00944/) (2020)
- [MindAgent: Emergent Gaming Interaction](https://mlsanity.com/paper/2309.09971/) (2023)
- [Cognitive Biases in Large Language Models: A Survey and Mitigation Experiments](https://mlsanity.com/paper/2412.00323/) (2024)
- [Argumentative Experience: Reducing Confirmation Bias on Controversial Issues through LLM-Generated Multi-Persona Debates](https://mlsanity.com/paper/2412.04629/) (2024)
- [A Human-Computer Collaborative Tool for Training a Single Large Language Model Agent into a Network through Few Examples](https://mlsanity.com/paper/2404.15974/) (2024)

## Built on by (most cited first, 19 of 19)

- [Multi-Agent Teams Hold Experts Back](https://mlsanity.com/paper/2602.01011/) (2026)
- [PerspectiveGap: A Benchmark for Multi-Agent Orchestration Prompting](https://mlsanity.com/paper/2606.08878/) (2026)
- [When Latent Agents Lie: KV-Cache Integrity in Multi-Agent LLM Collaboration](https://mlsanity.com/paper/2606.28958/) (2026)
- [When Truth Is Distributed: Misinformation Derails Collective Fact Recovery in LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2608.03421/) (2026)
- [Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation](https://mlsanity.com/paper/2605.01750/) (2026)
- [Theory of Scene: Breaking the Symmetry Trap in Multi-Agent LLM Coordination](https://mlsanity.com/paper/2609.32939/) (2026)
- [The Geometry of Dialogue: Graphing Language Models to Reveal Synergistic Teams for Multi-Agent Collaboration](https://mlsanity.com/paper/2510.26352/) (2025)
- [You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents](https://mlsanity.com/paper/2605.27586/) (2026)
- [Where Knowledge and Authority Sit Changes What an Agent Benchmark Can Resolve](https://mlsanity.com/paper/2607.02975/) (2026)
- [Consilience: Conformally Calibrated Communication Control for Hidden-Profile Multi-Agent Reasoning](https://mlsanity.com/paper/2608.20564/) (2026)
- [Proxifield: Decentralized Multi-Agent Communication through Semantic Proximity](https://mlsanity.com/paper/2609.20889/) (2026)
- [CAVEAT: Towards Robust Computer-Use Agents in Incentive-Misaligned Environments](https://mlsanity.com/paper/2609.27273/) (2026)
- [Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs](https://mlsanity.com/paper/2609.32259/) (2026)
- [Multi-agent discussion gains less when dissent is withheld](https://mlsanity.com/paper/2609.38324/) (2026)
- [Right Answers, Wrong States: Hidden Information Failures in Multi-Agent Collaboration](https://mlsanity.com/paper/2610.01244/) (2026)
- [Copies or Sources? Measuring How LLM Aggregators Count Restated Evidence in Multi-Agent Systems](https://mlsanity.com/paper/2610.06192/) (2026)
- [Agent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams](https://mlsanity.com/paper/2610.15788/) (2026)
- [Beyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues](https://mlsanity.com/paper/2610.16117/) (2026)
- [Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards](https://mlsanity.com/paper/2610.17893/) (2026)

## Abstract (arXiv)

Multi-agent systems built on large language models (LLMs) are expected to enhance decision-making by pooling distributed information, yet systematically evaluating this capability has remained challenging. We introduce HiddenBench, a 65-task benchmark grounded in the Hidden Profile paradigm, which isolates collective reasoning under distributed information from individual reasoning ability. Evaluating 15 frontier LLMs, we find that multi-agent LLMs achieve only 30.1% accuracy under distributed information, compared to 80.7% accuracy for single agents given complete information. We trace this gap to a systematic failure mode: agents cannot recognize or act under latent information asymmetry -- they fail to reason about what others might know but have not yet expressed, leading to premature convergence on shared evidence while critical distributed facts remain unexplored. These failures persist across prompting strategies, communication depths, and group sizes -- and worsen as groups scale. While some models (e.g., Gemini-2.5-Flash/Pro) outperform others, neither model scale nor individual reasoning accuracy reliably predicts collective performance. We further show that this bottleneck is actionable: a lightweight structured communication protocol substantially improves collective reasoning across model families. Our results identify failures in collective information exploration in decision-making as a key limitation of multi-agent LLMs, and provide a theory-grounded, reproducible framework for diagnosing collective reasoning failures.