mlsanityData to 7 Oct 2026

Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models

arXiv 2601.04651 ↗First posted 8 Jan 2026cs.AI cs.IR cs.MAcited by 2

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

Recent advances in synergizing large reasoning models (LRMs) with retrieval-augmented generation (RAG) have shown promising results, yet two critical challenges remain: (1) reasoning models typically operate from a single, unchallenged perspective, limiting their ability to conduct deep, self-correcting reasoning over external documents, and (2) existing training paradigms rely excessively on outcome-oriented rewards, which provide insufficient signal for shaping the complex, multi-step reasoning process. To address these issues, we propose an Reasoner-Verifier framework named Adversarial Reasoning RAG (ARR). The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other's logic while being guided by process-aware advantage that requires no external scoring model. This reward combines explicit observational signals with internal model uncertainty to jointly optimize reasoning fidelity and verification rigor. Experiments on multiple benchmarks demonstrate the effectiveness of our method.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 20 of its 33 references that are in the map. First posted on arXiv 8 Jan 2026.

Builds on

20 of 33 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward18 Aug
  2. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capability30 Apr
  3. 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning25 Mar
  4. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar
  5. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning7 Mar
  6. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan

Other references · 14

  1. 2025Qwen3 Technical Reportcited by 8,195
  2. 2024Qwen2.5 Technical Reportcited by 4,713
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  5. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  6. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  7. 2025The Entropy Mechanism of Reinforcement Learning for Reasoning Language Modelscited by 463
  8. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMscited by 377
  9. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learningcited by 357
  10. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 268
  11. 2025Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Modelscited by 134
  12. 2025Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RLcited by 75
2 more
  1. 2025WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflectioncited by 6
  2. 2025RE-Searcher: Robust Agentic Search with Goal-oriented Planning and Self-reflectioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Negative Advantages Is a Double-Edged Sword: Calibrating advantages in GRPO for Search Agentscited by 1
  2. 2026Retrieval, Reward, and Training Protocols: What Matters in Training Search Agents?cited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning
  2. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs
  3. 2024RAR-b: Reasoning as Retrieval Benchmark
  4. 2025UR2: Unify RAG and Reasoning through Reinforcement Learning
  5. 2026When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models
  6. 2025From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs
  7. 2025From Facts to Conclusions : Integrating Deductive Reasoning in Retrieval-Augmented LLMs
  8. 2025Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization