mlsanityData to 14 Oct 2026

DeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought Navigation

arXiv 2608.17282 ↗First posted 18 Aug 2026cs.AIcited by 0

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

Abstract (arXiv)

Existing agentic reasoning systems typically rely on centralized protocols. This design introduces routing bottlenecks and static role allocations that often fail when handling complex multimodal queries. We propose DeAR (Decentralized Agentic Reasoning), a framework that shifts from central control to autonomous peer-to-peer collaboration. DeAR is built on three mechanisms: (1) decentralized capability grounding for query-dependent agent specialization, (2) thought map navigation for targeted peer interactions, and (3) topology update for adaptive error correction. Evaluations across 9 diverse multimodal reasoning and text-based QA benchmarks indicate that DeAR consistently outperforms recent baseline methods, validating that decentralized and adaptive collaboration among agents enhances accuracy in knowledge-intensive reasoning tasks. The source code will be available at https://open_upon_acceptance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 30 of its 45 references that are in the map. First posted on arXiv 18 Aug 2026.

Builds on

30 of 45 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems10 Aug
  2. 2024Towards Rationality in Language and Multimodal Agents: A Survey1 Jun
  3. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration3 Oct

Other references · 27

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  5. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  6. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  7. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  8. 2025Gemma 3 Technical Reportcited by 1,824
  9. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  10. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,614
  11. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  12. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
15 more
  1. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  2. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  3. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  4. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  5. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 166
  6. 2024NVLM: Open Frontier-Class Multimodal LLMscited by 125
  7. 2025Removal of Hallucination on Hallucination: Debate-Augmented RAGcited by 29
  8. 2024AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistantcited by 27
  9. 2025ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QAcited by 13
  10. 2025SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflowscited by 13
  11. 2024A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoningcited by 11
  12. 2024MathLearner: A Large Language Model Agent Framework for Learning to Solve Mathematical Problemscited by 4
  13. 2025Multi-agent Undercover Gaming: Hallucination Removal via Counterfactual Test for Multimodal Reasoningcited by 4
  14. 2025Confidence-guided Refinement Reasoning for Zero-shot Question Answeringcited by 3
  15. 2026Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs
  2. 2026AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
  3. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
  4. 2025Reasoning-Aware Prompt Orchestration: A Foundation Model for Multi-Agent Language Model Coordination
  5. 2025Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs
  6. 2026G2CP: A Graph-Grounded Communication Protocol for Verifiable and Efficient Multi-Agent Reasoning
  7. 2025Consensus Is All You Need: Gossip-Based Reasoning Among Large Language Models
  8. 2025SwarmSys: Decentralized Swarm-Inspired Agents for Scalable and Adaptive Reasoning