Transparent and Robust RAG: Adaptive-Reward Reinforcement Learning for Decision Traceability

• URL: http://arxiv.org/abs/2505.13258v2
• Date: Sat, 11 Oct 2025 05:41:27 GMT
• Title: Transparent and Robust RAG: Adaptive-Reward Reinforcement Learning for Decision Traceability
• Authors: Jingyi Ren, Yekun Xu, Xiaolong Wang, Weitao Li, Weizhi Ma, Yang Liu,
• Abstract summary: Adaptive-Rewarded Evidence Navigation Agent (ARENA) is a transparent and robust RAG generator framework trained via RL with designed rewards.<n>Based on our structured protocol, KL divergence stabilization, and adaptive reward calculation modules, ARENA enables the RAG generator to identify key evidence, perform structured reasoning, and generate answers with interpretable decision traces.
• Score: 15.949084214401692
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval-Augmented Generation (RAG) delivers substantial value in knowledge-intensive applications. Many recent works use reinforcement learning (RL) to elicit strong reasoning in RAG generators. However, two key challenges remain unresolved: (1) Transparency: most prior methods do not explicitly indicate which references are actually used during the reasoning that leads to the final answer, limiting interpretability and visibility; (2) Stability: the KL divergence estimator used in existing RL-based approaches may cause gradient spikes, leading to unstable training. To address these challenges, we propose Adaptive-Rewarded Evidence Navigation Agent (ARENA), a transparent and robust RAG generator framework trained via RL with designed rewards. Based on our structured protocol, KL divergence stabilization, and adaptive reward calculation modules, ARENA enables the RAG generator to identify key evidence, perform structured reasoning, and generate answers with interpretable decision traces. Applied to Qwen2.5-7B-Instruct and Llama3.1-8B-Instruct, extensive experiments across multiple baselines show 10-30% accuracy improvements on three multi-hop QA datasets, comparable to advanced closed-source LLMs (e.g., OpenAI o1, DeepSeek R1). Further analyses show that ARENA generalizes well to unseen datasets and tasks. Our models and codes are publicly released.

Related papers

• Generative Reasoning Re-ranker [24.386586034456673]
  Generative Reasoning Reranker (GR2) is an end-to-end framework with a three-stage training pipeline tailored for reranking.<n> GR2 generates high-quality reasoning traces through carefully designed prompting and rejection sampling.<n>Experiments on two real-world datasets demonstrate GR2's effectiveness.
  arXiv  Detail & Related papers  (2026-02-08T02:12:24Z)
• Towards Sample-Efficient and Stable Reinforcement Learning for LLM-based Recommendation [56.92367609590823]
  Long Chain-of-Thought (Long CoT) reasoning has shown promise in Large Language Models (LLMs)<n>We argue that Long CoT is inherently ill-suited for the sequential recommendation domain.<n>We propose RISER, a novel Reinforced Item Space Exploration framework for Recommendation.
  arXiv  Detail & Related papers  (2026-01-31T10:02:43Z)
• From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation [52.62655622099456]
  We propose reinforcement learning with verifiable reference-based rewards (RLVRR)<n>Instead of checking the final answer, RLVRR extracts an ordered linguistic signal from high-quality references (i.e., reward chain)<n>In this way, RLVRR decomposes rewards into two dimensions: content, which preserves deterministic core concepts, and style, which evaluates adherence to stylistic properties.
  arXiv  Detail & Related papers  (2026-01-26T14:39:58Z)
• CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models [85.315711639214]
  We introduce Curiosity-Driven Exploration (CDE), a framework that leverages the model's own intrinsic sense of curiosity to guide exploration.<n>For the actor, we use perplexity over its generated response, and for the critic, we use the variance of value estimates from a multi-head architecture.<n>Our theoretical analysis shows that the actor-wise bonus inherently penalizes overconfident errors and promotes diversity among correct responses.
  arXiv  Detail & Related papers  (2025-09-11T17:59:17Z)
• The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward [57.56453588632619]
  A central paradox in fine-tuning Large Language Models (LLMs) with Reinforcement Learning with Verifiable Reward (RLVR) is the frequent degradation of multi-attempt performance.<n>This is often accompanied by catastrophic forgetting, where models lose previously acquired skills.<n>We argue that standard RLVR objectives lack a crucial mechanism for knowledge retention.
  arXiv  Detail & Related papers  (2025-09-09T06:34:32Z)
• From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs [13.410543801811992]
  This paper analyzes existing RAG reasoning models and identifies three main failure patterns.<n>We propose TIRESRAG-R1, a novel framework using a think-retrieve-reflect process and a multi-dimensional reward system.<n>Experiments on four multi-hop QA datasets show that TIRESRAG-R1 outperforms prior RAG methods and generalizes well to single-hop tasks.
  arXiv  Detail & Related papers  (2025-07-30T14:29:44Z)
• Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs [69.10441885629787]
  Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge.<n>It falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts.<n>This survey synthesizes both strands under a unified reasoning-retrieval perspective.
  arXiv  Detail & Related papers  (2025-07-13T03:29:41Z)
• LTRR: Learning To Rank Retrievers for LLMs [53.285436927963865]
  We show that routing-based RAG systems can outperform the best single-retriever-based systems.<n>Performance gains are especially pronounced in models trained with the Answer Correctness (AC) metric.<n>As part of the SIGIR 2025 LiveRAG challenge, our submitted system demonstrated the practical viability of our approach.
  arXiv  Detail & Related papers  (2025-06-16T17:53:18Z)
• Direct Reasoning Optimization: LLMs Can Reward And Refine Their Own Reasoning for Open-Ended Tasks [6.881699020319577]
  We propose Direct Reasoning Optimization (DRO), a reinforcement learning framework for fine-tuning Large Language Models (LLMs)<n>DRO is guided by a new reward signal: the Reasoning Reflection Reward (R3)<n>DRO consistently outperforms strong baselines while remaining broadly applicable across both open-ended and structured domains.
  arXiv  Detail & Related papers  (2025-06-16T10:43:38Z)
• ReVeal: Self-Evolving Code Agents via Iterative Generation-Verification [6.983144806500892]
  ReVeal is a multi-turn reinforcement learning framework that interleaves code generation with explicit self-verification and tool-based evaluation.<n>It fosters the co-evolution of a model's generation and verification capabilities through RL training, expanding the reasoning boundaries of the base model.<n>It also enables test-time scaling into deeper inference regimes, with code consistently evolving as the number of turns increases during inference.
  arXiv  Detail & Related papers  (2025-06-13T03:41:04Z)
• KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG [63.82127103851471]
  Retrieval-Augmented Generation (RAG) enables large language models to access broader knowledge sources.<n>We demonstrate that enhancing generative models' capacity to process noisy content is equally critical for robust performance.<n>We present KARE-RAG, which improves knowledge utilization through three key innovations.
  arXiv  Detail & Related papers  (2025-06-03T06:31:17Z)
• R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning [60.17074283370798]
  Retrieval-Augmented Generation (RAG) integrates external knowledge with Large Language Models (LLMs) to enhance factual correctness and hallucination.<n>We propose $textbfR3-RAG$, which uses $textbfR$einforcement learning to make the LLM learn how to $textbfR$eason and $textbfR$etrieve step by step, thus retrieving comprehensive external knowledge and leading to correct answers.
  arXiv  Detail & Related papers  (2025-05-26T12:25:37Z)
• Learning to Reason without External Rewards [100.27210579418562]
  Training large language models (LLMs) for complex reasoning via Reinforcement Learning with Verifiable Rewards (RLVR) is effective but limited by reliance on costly, domain-specific supervision.<n>We explore Reinforcement Learning from Internal Feedback (RLIF), a framework that enables LLMs to learn from intrinsic signals without external rewards or labeled data.<n>We propose Intuitor, an RLIF method that uses a model's own confidence, termed self-certainty, as its sole reward signal.
  arXiv  Detail & Related papers  (2025-05-26T07:01:06Z)
• Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning [45.10424242207931]
  Retrieval-augmented generation (RAG) enhances the text generation capabilities of large language models (LLMs)<n>We introduce a novel method ReasonRAG that automatically constructs RAG-ProGuide, a high-quality dataset providing process-level rewards for query generation, evidence extraction, and answer generation.<n>With the process-level policy optimization, the proposed framework empowers LLMs to autonomously invoke search, generate queries, extract relevant evidence, and produce final answers.
  arXiv  Detail & Related papers  (2025-05-20T08:21:00Z)
• Observe-R1: Unlocking Reasoning Abilities of MLLMs with Dynamic Progressive Reinforcement Learning [3.364797975300393]
  We present Observe-R1, a novel framework aimed at enhancing the reasoning capabilities of multimodal large language models (MLLMs)<n>We construct the NeuraLadder dataset, which is organized and sampled according to the difficulty and complexity of data samples for RL training.<n>Experiments with the Qwen2.5-VL-3B and Qwen2.5-VL-7B models on 20k samples from the NeuraLadder dataset show that Observe-R1 outperforms a series of larger reasoning models on both reasoning and general benchmarks.
  arXiv  Detail & Related papers  (2025-05-18T14:08:03Z)
• Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models [83.8639566087953]
  We propose a direct retrieval-augmented optimization framework, named DRO, that enables end-to-end training of two key components.<n>DRO alternates between two phases: (i) document permutation estimation and (ii) re-weighted, progressively improving RAG components.<n>Our theoretical analysis reveals that DRO is analogous to policy-gradient methods in reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-05T23:54:53Z)
• RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning [125.96848846966087]
  Training large language models (LLMs) as interactive agents presents unique challenges.<n>While reinforcement learning has enabled progress in static tasks, multi-turn agent RL training remains underexplored.<n>We propose StarPO, a general framework for trajectory-level agent RL, and introduce RAGEN, a modular system for training and evaluating LLM agents.
  arXiv  Detail & Related papers  (2025-04-24T17:57:08Z)
• Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization [97.72503890388866]
  We propose Self-Routing RAG (SR-RAG), a novel framework that binds selective retrieval with knowledge verbalization.<n>SR-RAG enables an LLM to dynamically decide between external retrieval and verbalizing its own parametric knowledge.<n>We introduce dynamic knowledge source inference via nearest neighbor search to improve the accuracy of knowledge source decision.
  arXiv  Detail & Related papers  (2025-04-01T17:59:30Z)
• Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains [92.36624674516553]
  Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs)<n>We investigate the effectiveness and scalability of RLVR across diverse real-world domains including medicine, chemistry, psychology, economics, and education.<n>We utilize a generative scoring technique that yields soft, model-based reward signals to overcome limitations posed by binary verifications.
  arXiv  Detail & Related papers  (2025-03-31T08:22:49Z)
• OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement [91.88062410741833]
  This study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs)<n>We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization.<n>OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrates the potential of our strategy for robust vision-language reasoning.
  arXiv  Detail & Related papers  (2025-03-21T17:52:43Z)
• RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning [11.872929831119661]
  We introduce RAG-RL, the first reasoning language model (RLM) specifically trained for retrieval-augmented generation (RAG) settings.<n>RAG-RL demonstrates that stronger answer generation models can identify relevant contexts within larger sets of retrieved information.<n>We show that curriculum design in the reinforcement learning (RL) post-training process is a powerful approach to enhancing model performance.
  arXiv  Detail & Related papers  (2025-03-17T02:53:42Z)
• MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning [55.82649731348012]
  We introduce the MMK12 dataset and MM-EUREKA with 7B and 32B parameters.<n>The former is a high-quality multimodal mathematics reasoning dataset featuring diverse knowledge domains with human-verified answers and solution processes.<n>The latter is a multimodal model employing rule-based reinforcement learning utilizing online filtering and two-stage training strategy to enhance training stability.
  arXiv  Detail & Related papers  (2025-03-10T14:23:12Z)
• RAG-Reward: Optimizing RAG with Reward Modeling and RLHF [8.911260109659489]
  Retrieval-augmented generation (RAG) enhances Large Language Models (LLMs) with relevant and up-to-date knowledge.<n>The role of reward models in reinforcement learning for optimizing RAG remains underexplored.<n>We introduce textbfRAG-Reward, a framework designed to develop reward models.
  arXiv  Detail & Related papers  (2025-01-22T22:59:19Z)
• Retrieval-Augmented Generation for Large Language Models: A Survey [17.82361213043507]
  Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by incorporating knowledge from external databases.
  arXiv  Detail & Related papers  (2023-12-18T07:47:33Z)

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.