From Verdict to Process: Agentic Reinforcement Learning for Multi-Stage Fact Verification

• URL: http://arxiv.org/abs/2606.13262v1
• Date: Thu, 11 Jun 2026 12:17:18 GMT
• Title: From Verdict to Process: Agentic Reinforcement Learning for Multi-Stage Fact Verification
• Abstract summary: We propose ProFact, an agentic reinforcement learning framework for end-to-end optimization of multi-stage fact verification trajectories.<n>ProFact trains a unified policy to coordinate claim decomposition, evidence seeking, answer generation, and verdict prediction.<n> Empirical evaluation shows that ProFact consistently outperforms strong baselines in both verification performance and inference efficiency.
• Score: 4.539896456749749
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent approaches combining Large Language Models (LLMs) with retrieval-augmented reasoning have shown promise for automated fact verification. To process complex claims, these verification pipelines typically execute multi-stage workflows that coordinate tightly coupled modules, including claim decomposition, evidence gathering, and verdict prediction. However, existing methods optimize individual stages in isolation or rely on fixed heuristics, which limits adaptive coordination among stages and can lead to suboptimal outcomes. In this work, we propose ProFact, an agentic reinforcement learning framework for end-to-end optimization of multi-stage fact verification trajectories. ProFact trains a unified policy to coordinate claim decomposition, evidence seeking, answer generation, and verdict prediction. To address the sparse and delayed supervision provided by final veracity labels, ProFact introduces process-aware rewards that provide stage-level learning signals throughout the verification process. Empirical evaluation shows that ProFact consistently outperforms strong baselines in both verification performance and inference efficiency. These results highlight the effectiveness of process-aware trajectory optimization for multi-stage fact verification.

Related papers

• TROVE: Adaptive Agent Skill Orchestration via Trace-Grounded Route Validation and Editing [14.424308190797683]
  We propose Trace-grounded Route Orchestration via Validation and Editing (TROVE)<n> Offline, TROVE distills evaluated workflow-search traces into atomic and composite skills and an outcome-conditioned transition graph.<n>Online, it treats a planned route as provisional, after committing one top-level skill, the controller retains a valid continuation, inserts a trace-supported local response, or replaces only the invalid suffix.
  arXiv  Detail & Related papers  (2026-09-04T11:38:13Z)
• Efficient Test-Time Optimization for Multi-Agent Proof Autoformalization [20.22828310618122]
  ToMap is a framework that structures proof autoformalization as a Decomposer-Formalizer-Prover pipeline.<n>We show that ToMap improves over the best previous method by 19.0% when evaluated by both syntactic correctness and semantic faithfulness.
  arXiv  Detail & Related papers  (2026-07-13T09:21:15Z)
• Self-Improving In-Context Learning [3.9202238580555417]
  We propose to improve in-context learning by optimizing the embeddings of a few prompt test at time.<n>We formalize this signal as a bounded, self-supervised calibration procedure.<n>Across a comprehensive suite of ICL tasks, the proposed calibration improves or matches upon the base model and consistently outperforms classification-specific baselines on most tasks.
  arXiv  Detail & Related papers  (2026-05-22T03:01:34Z)
• Evaluate-as-Action: Self-Evaluated Process Rewards for Retrieval-Augmented Agents [24.080021799509847]
  textscEvalAct (Evaluate-as-Action) converts implicit retrieval quality assessment into an explicit action.<n>textscEvalAct achieves the best average accuracy, with the largest gains on multi-hop tasks.
  arXiv  Detail & Related papers  (2026-03-10T05:22:40Z)
• Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement [24.721024438862553]
  CoFiCot is a coarse-to-fine adaptive framework that tailors inference strategies to problem difficulty.<n>We implement a multi-metric classifier that triages queries by semantic entropy, consensus reliability, and predicted reasoning depth.<n>This enables a differentiated refinement stage that applies efficient aggregation for simple queries while routing complex ones to a context-aware correction loop.
  arXiv  Detail & Related papers  (2026-03-09T11:23:07Z)
• Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols [123.73663884421272]
  Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.<n>We establish FEWTRANS, a comprehensive benchmark containing 10 diverse datasets.<n>By releasing FEWTRANS, we aim to provide a rigorous "ruler" to streamline reproducible advances in few-shot transfer learning research.
  arXiv  Detail & Related papers  (2026-02-28T05:41:57Z)
• Rectifying LLM Thought from Lens of Optimization [48.98086817378953]
  Long chain-of-thought (CoT) prompting enables thorough exploration and deliberation.<n>Despite advances, long-CoT LLMs often exhibit suboptimal reasoning behaviors.<n>We introduce RePro, a novel approach to refine LLM reasoning during post-training.
  arXiv  Detail & Related papers  (2025-12-01T17:41:08Z)
• Prompt Optimization via Retrieved Reasoning Assets and Multi-Agent Analysis [5.935239028627343]
  We introduce MA-SAPO, a Multi-Agent framework for Score-Aware Prompt Optimization.<n>Compared to prior methods, MA-SAPO explicitly couples evaluation outcomes with structured reasoning to guide systematic edits.<n>By turning evaluation signals into interpretable reasoning chains, MA-SAPO produces prompt refinements that are more transparent, auditable, and controllable.
  arXiv  Detail & Related papers  (2025-10-18T20:21:09Z)
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)
• In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement [71.60563181678323]
  Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality.<n>To handle these challenges, a direct solution is to generate high-confidence'' data from unsupervised downstream tasks.<n>We propose a novel approach, pseudo-supervised demonstrations aligned prompt optimization (PAPO) algorithm, which jointly refines both the prompt and the overall pseudo-supervision.
  arXiv  Detail & Related papers  (2024-10-04T03:39:28Z)
• Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo [55.452453947359736]
  We introduce a novel verification method based on Twisted Sequential Monte Carlo (TSMC)<n>We apply TSMC to Large Language Models by estimating the expected future rewards at partial solutions.<n>This approach results in a more straightforward training target that eliminates the need for step-wise human annotations.
  arXiv  Detail & Related papers  (2024-10-02T18:17:54Z)
• FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment [93.09267863425492]
  We argue that understanding both high-level semantics and internal temporal structures of actions in competitive sports videos is the key to making predictions accurate and interpretable. We construct a new fine-grained dataset, called FineDiving, developed on diverse diving events with detailed annotations on action procedures.
  arXiv  Detail & Related papers  (2022-04-07T17:59:32Z)

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.