mlsanityData to 7 Oct 2026

DPBench: Structural Determinants of Multi-Agent LLM Coordination Under Simultaneous Resource Contention

arXiv 2602.13255 ↗First posted 2 Feb 2026cs.AI cs.MAcited by 1

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

We present DPBench, a benchmark for evaluating coordination in multi-agent systems built from large language models. Existing benchmarks measure task-level success under a fixed protocol; the structural conditions under which coordination succeeds or fails at all have not been characterised. DPBench adapts the Dining Philosophers problem into a controlled testbed where the action protocol, the communication structure, and the group size each vary independently. We evaluate six agents: GPT-5.2, Claude Opus 4.5, Grok 4.1, Gemini 2.5 Flash, Llama 4 Maverick, and a uniform-random baseline. Under simultaneous action at N=5 with the default prompt, deadlock ranges from 25.0% (95% Wilson CI [11.2, 46.9]) for GPT-5.2 to 90.0% [74.4, 96.5] for Gemini 2.5 Flash; sequential action is solved by four of the six. Holding the model fixed at Gemini 2.5 Flash, three protocol variables drive deadlock from 90% to within CI of zero: three rounds of pre-commitment communication (0.0% vs. single-round 86.7%), a prompt encoding a classical concurrency primitive (0.0% for resource-ordering and symmetry-breaking, against 100% for the minimal prompt), or doubling the group from N=5 to N=10 (90.0% to 10.0%). Single-round messaging and memory of past timesteps do not change the rate at the sample size we ran. Whether the same model coordinates or deadlocks is determined by the protocol, not by the model's capability.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 35 of its 47 references that are in the map. First posted on arXiv 2 Feb 2026.

Builds on

35 of 47 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents3 Mar
  2. 2024Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication25 Sep
  3. 2024Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models9 Jul
  4. 2024Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues29 Jan
  5. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models6 Oct
  6. 2023LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models5 Oct
  7. 2023AgentBench: Evaluating LLMs as Agents7 Aug
  8. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug

Other references · 27

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  7. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  8. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 915
  9. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  10. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 561
  11. 2024GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Modelscited by 533
  12. 2024AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agentscited by 406
15 more
  1. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 372
  2. 2016Learning Multiagent Communication with Backpropagationcited by 355
  3. 2023On the Planning Abilities of Large Language Models : A Critical Investigationcited by 308
  4. 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 265
  5. 2020"Other-Play" for Zero-Shot Coordinationcited by 194
  6. 2024MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Makingcited by 162
  7. 2024On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Taskscited by 137
  8. 2024Secret Collusion among AI Agents: Multi-Agent Deception via Steganographycited by 107
  9. 2023HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Modelscited by 61
  10. 2024OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Modelscited by 54
  11. 2019Biases for Emergent Communication in Multi-agent Reinforcement Learningcited by 48
  12. 2021Emergent Communication of Generalizationscited by 41
  13. 2024Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learningcited by 32
  14. 2023ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordinationcited by 23
  15. 2025ASTRA: A Negotiation Agent with Adaptive and Strategic Reasoning via Tool-integrated Action for Dynamic Offer Optimizationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligencecited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems
  2. 2026MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability
  3. 2026Benchmarking Open-Ended Multi-Agent Coordination in Language Agents
  4. 2026Benchmarking Emergent Coordination in Large-Scale LLM Populations: An Evaluation Framework on the MoltBook Archive
  5. 2026More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration
  6. 2026COOP2: Defining, Observing, and Repairing Cooperation in LLM Multi-Agent Systems
  7. 2024BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systems
  8. 2025Can LLM Agents Solve Collaborative Tasks? A Study on Urgency-Aware Planning and Coordination