MetaRAG: Belief-Action Aligned Policy Optimization for Agentic RAG

• URL: http://arxiv.org/abs/2608.24214v1
• Date: Tue, 25 Aug 2026 08:20:29 GMT
• Title: MetaRAG: Belief-Action Aligned Policy Optimization for Agentic RAG
• Abstract summary: Agentic retrieval-augmented generation (RAG) requires language models to decide when to continue searching and when to answer.<n>Existing RL-based methods rely on external supervision and overlook the agent's internal belief about whether the current evidence is sufficient.<n>We propose MetaRAG, a belief-action policy optimization framework for agentic RAG.
• Score: 20.308039818816777
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agentic retrieval-augmented generation (RAG) requires language models to decide when to continue searching and when to answer. Existing RL-based methods rely on external supervision and overlook the agent's internal belief about whether the current evidence is sufficient. To address this problem, we reformulate the search decision quality as belief-action alignment and propose MetaRAG, a belief-action aligned policy optimization framework for agentic RAG. MetaRAG uses Verify-first Action Generation to elicit an explicit verification process before each actual action, and Internal Belief Probing to estimate the policy model's own answerability belief from the same question-history context. Based on these, MetaRAG derives a consistency reward that is further gated by answer correctness, avoiding reinforcement of internally consistent but incorrect trajectories. The belief probe is used only during training and introduces no inference-time overhead. Experiments on seven public QA benchmarks show that MetaRAG consistently improves the accuracy-efficiency trade-off over strong RL-based agentic RAG baselines, with gains that transfer to deep research settings, different optimizers, and multiple model backbones.

Related papers

• ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning [74.19730275669227]
  ARISE-RL is a novel full-cycle self-evolution framework for training open-ended agents.<n>We present Reward-Gated Self-Evolution Distillation (RG-SED), which distills a memory-augmented variant of the same policy back into itself.<n>We also present ECR-Bench, an expert-calibrated rubric benchmark suite covering single-tool deep research and multi-tool travel planning.
  arXiv  Detail & Related papers  (2026-09-01T10:54:13Z)
• Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals [75.25256166997414]
  We introduce Metacognition-as-Reward (MaR), a metacognition-inspired RL framework.<n>MaR guides reasoning through two general process dimensions.<n>MaR consistently improves model performance, achieving up to a 7.7% gain over the base model.
  arXiv  Detail & Related papers  (2026-05-22T08:54:37Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models [29.703793991791674]
  Existing RAG-oriented reinforcement learning methods rely on external rewards that often fail to evaluate document faithfulness.<n>We propose a novel "internal-external" hybrid reward framework centered on a Contrastive Likelihood Reward (CLR)<n>CLR directly optimize the log-likelihood gap between responses conditioned on prompts with and without supporting evidence.
  arXiv  Detail & Related papers  (2026-02-02T12:21:59Z)
• FAIR-RAG: Faithful Adaptive Iterative Refinement for Retrieval-Augmented Generation [0.0]
  We introduce FAIR-RAG, a novel agentic framework that transforms the standard RAG pipeline into a dynamic, evidence-driven reasoning process.<n>We conduct experiments on challenging multi-hop QA benchmarks, including HotpotQA, 2WikiMultiHopQA, and MusiQue.<n>Our work demonstrates that a structured, evidence-driven refinement process with explicit gap analysis is crucial for unlocking reliable and accurate reasoning in advanced RAG systems.
  arXiv  Detail & Related papers  (2025-10-25T15:59:33Z)
• Enhancing Retrieval Augmentation via Adversarial Collaboration [50.117273835877334]
  We propose the Adrial Collaboration RAG (AC-RAG) framework to address "Retrieval Hallucinations"<n>AC-RAG employs two heterogeneous agents: a generalist Detector that identifies knowledge gaps, and a domain-specialized Resolver that provides precise solutions.<n>Experiments show that AC-RAG significantly improves retrieval accuracy and outperforms state-of-the-art RAG methods across various vertical domains.
  arXiv  Detail & Related papers  (2025-09-18T08:54:20Z)
• SIRAG: Towards Stable and Interpretable RAG with A Process-Supervised Multi-Agent Framework [7.37561751991963]
  We propose a process-supervised multi-agent framework to bridge the gap between retriever and generator.<n>The proposed framework is modular and plug-and-play, requiring no modification to the retriever or generator.
  arXiv  Detail & Related papers  (2025-09-17T09:09:28Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• RAG-Gym: Systematic Optimization of Language Agents for Retrieval-Augmented Generation [43.50113345998687]
  We introduce RAG-Gym, a comprehensive platform that explores three optimization dimensions: (1) prompt engineering, (2) actor tuning, and (3) critic training.<n>For prompt engineering, we propose Re$2$Search, a novel agent incorporating reflection reasoning that significantly outperforms standard prompts.<n>In actor tuning, we evaluate three popular post-training algorithms with fine-grained process supervision and identify direct preference optimization as the most effective.
  arXiv  Detail & Related papers  (2025-02-19T18:56:03Z)
• Chain-of-Retrieval Augmented Generation [91.02950964802454]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.