PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering

• URL: http://arxiv.org/abs/2601.05465v1
• Date: Fri, 09 Jan 2026 01:38:38 GMT
• Title: PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering
• Authors: Yu Liu, Wenxiao Zhang, Cong Cao, Wenxuan Lu, Fangfang Yuan, Diandian Guo, Kun Peng, Qiang Sun, Kaiyan Zhang, Yanbing Liu, Jin B. Hong, Bowen Zhou, Zhiyuan Ma,
• Abstract summary: Answering real-world open-domain questions over massive corpora is a critical challenge in Retrieval-Augmented Generation (RAG) systems.<n>Recent research employs reinforcement learning (RL) to end-to-end optimize the retrieval-augmented reasoning process.<n>We propose PRISMA, a decoupled-guided framework featuring a Plan-Retrieve-Inspect-Memoize architecture.
• Score: 26.994531058178982
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Answering real-world open-domain multi-hop questions over massive corpora is a critical challenge in Retrieval-Augmented Generation (RAG) systems. Recent research employs reinforcement learning (RL) to end-to-end optimize the retrieval-augmented reasoning process, directly enhancing its capacity to resolve complex queries. However, reliable deployment is hindered by two obstacles. 1) Retrieval Collapse: iterative retrieval over large corpora fails to locate intermediate evidence containing bridge answers without reasoning-guided planning, causing downstream reasoning to collapse. 2) Learning Instability: end-to-end trajectory training suffers from weak credit assignment across reasoning chains and poor error localization across modules, causing overfitting to benchmark-specific heuristics that limit transferability and stability. To address these problems, we propose PRISMA, a decoupled RL-guided framework featuring a Plan-Retrieve-Inspect-Solve-Memoize architecture. PRISMA's strength lies in reasoning-guided collaboration: the Inspector provides reasoning-based feedback to refine the Planner's decomposition and fine-grained retrieval, while enforcing evidence-grounded reasoning in the Solver. We optimize individual agent capabilities via Two-Stage Group Relative Policy Optimization (GRPO). Stage I calibrates the Planner and Solver as specialized experts in planning and reasoning, while Stage II utilizes Observation-Aware Residual Policy Optimization (OARPO) to enhance the Inspector's ability to verify context and trigger targeted recovery. Experiments show that PRISMA achieves state-of-the-art performance on ten benchmarks and can be deployed efficiently in real-world scenarios.

Related papers

• 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)
• ProRAG: Process-Supervised Reinforcement Learning for Retrieval-Augmented Generation [54.071574153853994]
  ProRAG is a process-supervised reinforcement learning framework designed to integrate learned step-level supervision into the online optimization loop.<n>Our framework consists of four stages: (1) Supervised Policy Warmup to initialize the model with a structured reasoning format; (2) construction of an MCTS-based Process Reward Model (PRM) to quantify intermediate reasoning quality; (3) PRM-Guided Reasoning Refinement to align the policy with fine-grained process preferences; and (4) Process-Supervised Reinforcement Learning with a dual-granularity advantage mechanism.
  arXiv  Detail & Related papers  (2026-01-29T16:04:59Z)
• When should I search more: Adaptive Complex Query Optimization with Reinforcement Learning [26.489185170468062]
  We propose a novel RL framework called Adaptive Complex Query Optimization (ACQO)<n>Our framework is designed to adaptively determine when and how to expand the search process.<n>ACQO achieves state-of-the-art performance on three complex query benchmarks, significantly outperforming established baselines.
  arXiv  Detail & Related papers  (2026-01-29T03:16:53Z)
• Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning [137.33138614095435]
  Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models.<n>Recent efforts have incorporated search-based interactions into RAG, enabling iterative reasoning with real-time retrieval.<n>We propose Bi-RAR, a novel retrieval-augmented reasoning framework that evaluates each intermediate step jointly in both forward and backward directions.
  arXiv  Detail & Related papers  (2025-11-12T08:29:39Z)
• Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMs [23.590034731179824]
  We present Through Role Orchestration (Maestro), a principled paradigm for collaboration that structurally decouples cognitive modes.<n>Maestro uses a collective of parallel Execution Agents for diverse exploration and a specialized Central Agent for convergent, evaluative synthesis.<n>Experiments on mathematical reasoning and general problem-solving benchmarks demonstrate that Maestro, coupled with CLPO, consistently outperforms existing state-of-the-art multi-agent approaches.
  arXiv  Detail & Related papers  (2025-11-08T21:01:27Z)
• VAR: Visual Attention Reasoning via Structured Search and Backtracking [49.427842994857635]
  We introduce Visual Attention Reasoning, a framework that recasts grounded reasoning as a structured search.<n> VAR decomposes the reasoning process into two key stages: traceable evidence grounding and search-based chain-of-thought.<n>We show that our 7B model, VAR-7B, sets a new state-of-the-art on a comprehensive suite of hallucination and safety benchmarks.
  arXiv  Detail & Related papers  (2025-10-21T13:18:44Z)
• From <Answer> to <Think>: Multidimensional Supervision of Reasoning Process for LLM Optimization [62.07990937720985]
  Dimension-level Reward Model (DRM) is a new supervision framework for Large Language Models.<n>DRM evaluates the quality of a reasoning process along three fundamental, complementary, and interpretable dimensions.<n> Experimental results show that DRM provides effective supervision signals, guides the optimization of LLMs and enhances their reasoning ability.
  arXiv  Detail & Related papers  (2025-10-13T14:29:15Z)
• UR$^2$: Unify RAG and Reasoning through Reinforcement Learning [17.319590573147565]
  Large Language Models (LLMs) have shown remarkable capabilities through two complementary paradigms: Retrieval-Augmented Generation (RAG) and Reinforcement Learning from Verifiable Rewards (RLVR)<n>We propose UR2 (Unified RAG and Reasoning), a general framework that unifies retrieval and reasoning through reinforcement learning.<n>Experiments across open-domain QA, MMLU-Pro, medical, and mathematical reasoning tasks demonstrate that UR$2$ significantly outperforms existing RAG and RL methods.
  arXiv  Detail & Related papers  (2025-08-08T09:33:20Z)
• PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning [57.89188317734747]
  PrismRAG trains the model with distractor-aware QA pairs mixing gold evidence with subtle distractor passages.<n>It instills reasoning-centric habits that make the LLM plan, rationalize, and synthesize without relying on extensive human engineered instructions.
  arXiv  Detail & Related papers  (2025-07-25T00:15:31Z)
• HiRA: A Hierarchical Reasoning Framework for Decoupled Planning and Execution in Deep Search [85.12447821237045]
  HiRA is a hierarchical framework that separates strategic planning from specialized execution.<n>Our approach decomposes complex search tasks into focused subtasks, assigns each subtask to domain-specific agents equipped with external tools and reasoning capabilities.<n> Experiments on four complex, cross-modal deep search benchmarks demonstrate that HiRA significantly outperforms state-of-the-art RAG and agent-based systems.
  arXiv  Detail & Related papers  (2025-07-03T14:18:08Z)

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.