HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation

• URL: http://arxiv.org/abs/2510.07794v1
• Date: Thu, 09 Oct 2025 05:13:10 GMT
• Title: HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
• Authors: Peilin Wu, Mian Zhang, Kun Wan, Wentian Zhao, Kaiyu He, Xinya Du, Zhiyu Chen,
• Abstract summary: suboptimal search behaviors exist widely, such as over-search and under-search.<n>Current training methods, which typically rely on outcome-based rewards in a RL framework, lack the fine-grained control needed to address these inefficiencies.<n>We introduce HiPRAG, a training methodology that incorporates a fine-grained, knowledge-grounded process reward into the RL training.
• Score: 21.08814504507274
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Agentic RAG is a powerful technique for incorporating external information that LLMs lack, enabling better problem solving and question answering. However, suboptimal search behaviors exist widely, such as over-search (retrieving information already known) and under-search (failing to search when necessary), which leads to unnecessary overhead and unreliable outputs. Current training methods, which typically rely on outcome-based rewards in a RL framework, lack the fine-grained control needed to address these inefficiencies. To overcome this, we introduce Hierarchical Process Rewards for Efficient agentic RAG (HiPRAG), a training methodology that incorporates a fine-grained, knowledge-grounded process reward into the RL training. Our approach evaluates the necessity of each search decision on-the-fly by decomposing the agent's reasoning trajectory into discrete, parsable steps. We then apply a hierarchical reward function that provides an additional bonus based on the proportion of optimal search and non-search steps, on top of commonly used outcome and format rewards. Experiments on the Qwen2.5 and Llama-3.2 models across seven diverse QA benchmarks show that our method achieves average accuracies of 65.4% (3B) and 67.2% (7B). This is accomplished while improving search efficiency, reducing the over-search rate to just 2.3% and concurrently lowering the under-search rate. These results demonstrate the efficacy of optimizing the reasoning process itself, not just the final outcome. Further experiments and analysis demonstrate that HiPRAG shows good generalizability across a wide range of RL algorithms, model families, sizes, and types. This work demonstrates the importance and potential of fine-grained control through RL, for improving the efficiency and optimality of reasoning for search agents.

Related papers

• Exploring Reasoning Reward Model for Agents [30.458783880389216]
  Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use.<n>Most methods still relies on sparse outcome-based reward for training.<n>We introduce Agent Reasoning Reward Model (Agent-RRM), a multi-faceted reward model that produces structured feedback for agentic trajectories.
  arXiv  Detail & Related papers  (2026-01-29T18:59:52Z)
• SmartSearch: Process Reward-Guided Query Refinement for Search Agents [63.46067892354375]
  Large language model (LLM)-based search agents have proven promising for addressing knowledge-intensive problems.<n>Existing works largely focus on optimizing the reasoning paradigms of search agents, yet the quality of intermediate search queries during reasoning remains overlooked.<n>We introduce SmartSearch, a framework built upon two key mechanisms to mitigate this issue.
  arXiv  Detail & Related papers  (2026-01-08T12:39:05Z)
• ROAD: Reflective Optimization via Automated Debugging for Zero-Shot Agent Alignment [1.6968020497268546]
  ROAD is a novel framework that treats optimization as a dynamic debug investigation rather than a search.<n>Road is highly sample-efficient, achieving a 5.6 percent increase in success rate and a 3.8 percent increase in search accuracy.<n>These findings suggest that mimicking the human engineering loop of failure analysis and patching offers a viable, data-efficient alternative to resource-intensive training.
  arXiv  Detail & Related papers  (2025-12-30T07:31:34Z)
• Multimodal Reinforcement Learning with Agentic Verifier for AI Agents [131.46008226323423]
  Argos is a principled multimodal reward agent to train reasoning models for agentic tasks.<n>By leveraging our agentic verifier across both SFT data and RL training, our model achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2025-12-03T04:42:47Z)
• WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking [60.35109192765302]
  Information seeking is a core capability that enables autonomous reasoning and decision-making.<n>We propose WebLeaper, a framework for constructing high-coverage IS tasks and generating efficient solution trajectories.<n>Our method consistently achieves improvements in both effectiveness and efficiency over strong baselines.
  arXiv  Detail & Related papers  (2025-10-28T17:51:42Z)
• Demystifying Reinforcement Learning in Agentic Reasoning [90.3737088727791]
  We conduct a comprehensive and systematic investigation to demystify reinforcement learning in agentic reasoning.<n>We highlight our key insights: (i) replacing stitched synthetic trajectories with real end-to-end tool-use trajectories yields a far stronger SFT.<n> Exploration-friendly techniques are crucial for agentic RL, such as clip higher, overlong reward shaping, and maintaining adequate policy entropy could improve the training efficiency.
  arXiv  Detail & Related papers  (2025-10-13T17:57:15Z)
• Beneficial Reasoning Behaviors in Agentic Search and Effective Post-training to Obtain Them [23.986035712600657]
  We propose a reasoning-driven pipeline to study effective reasoning behavior patterns in agentic search.<n>We identify four beneficial reasoning behaviors: Information Verification, Authority Evaluation, Adaptive Search, and Error Recovery.<n>We show that behavior priming yields over 35% gains in Llama3.2-3B and Qwen3-1.7B compared to directly training agentic search models with RL.
  arXiv  Detail & Related papers  (2025-10-08T00:20:35Z)
• DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision [50.89715397781075]
  Agentic Retrieval-Augmented Generation (Agentic RAG) enhances the processing capability for complex tasks.<n>We propose DecEx-RAG, which models RAG as a Markov Decision Process (MDP) incorporating decision-making and execution.<n>We show that DecEx-RAG achieves an average absolute performance improvement of $6.2%$ across six datasets.
  arXiv  Detail & Related papers  (2025-10-07T08:49:22Z)
• Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents [19.31471304268234]
  We introduce DeSA (Decoupling Search-and-Answering), a simple two-stage training framework that explicitly separates search optimization from answer generation.<n>Across seven QA benchmarks, DeSA-trained agents consistently improve search behaviors, delivering substantially higher search recall and answer accuracy than outcome-only baselines.
  arXiv  Detail & Related papers  (2025-10-06T11:09:45Z)
• Your Reward Function for RL is Your Best PRM for Search: Unifying RL and Search-Based TTS [62.22644307952087]
  We introduce AIRL-S, the first natural unification of RL-based and search-based TTS.<n>We leverage adversarial inverse reinforcement learning (AIRL) combined with group relative policy optimization (GRPO) to learn a dense, dynamic PRM directly from correct reasoning traces.<n>Our results show that our unified approach improves performance by 9 % on average over the base model, matching GPT-4o.
  arXiv  Detail & Related papers  (2025-08-19T23:41:15Z)
• AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Search [58.98450205734779]
  Large language model (LLM) agents have demonstrated strong capabilities across diverse domains.<n>Existing agent search methods suffer from three major limitations.<n>We introduce a comprehensive framework to address these challenges.
  arXiv  Detail & Related papers  (2025-06-06T12:07:23Z)
• RRO: LLM Agent Optimization Through Rising Reward Trajectories [52.579992804584464]
  Large language models (LLMs) have exhibited extraordinary performance in a variety of tasks.<n>In practice, agents sensitive to the outcome of certain key steps which makes them likely to fail the task.<n>We propose Reward Rising Optimization (RRO) to mitigate this issue.
  arXiv  Detail & Related papers  (2025-05-27T05:27:54Z)
• Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty [21.96443267949563]
  Agentic Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by enabling dynamic, multi-step reasoning and information retrieval.<n>These systems often exhibit sub-optimal search behaviors like over-search (retrieving redundant information) and under-search (failing to retrieve necessary information)<n>This work formally defines and quantifies these behaviors, revealing their prevalence across multiple QA datasets and agentic RAG systems.
  arXiv  Detail & Related papers  (2025-05-22T20:57:56Z)
• 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)
• Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning [55.96599486604344]
  We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process. We use Monte Carlo Tree Search (MCTS) to iteratively collect preference data, utilizing its look-ahead ability to break down instance-level rewards into more granular step-level signals. The proposed algorithm employs Direct Preference Optimization (DPO) to update the LLM policy using this newly generated step-level preference data.
  arXiv  Detail & Related papers  (2024-05-01T11:10:24Z)
• Learning to Optimize for Reinforcement Learning [58.01132862590378]
  Reinforcement learning (RL) is essentially different from supervised learning, and in practice, these learneds do not work well even in simple RL tasks. Agent-gradient distribution is non-independent and identically distributed, leading to inefficient meta-training. We show that, although only trained in toy tasks, our learned can generalize unseen complex tasks in Brax.
  arXiv  Detail & Related papers  (2023-02-03T00:11:02Z)

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.