# OpenFC: Learning Verification Policies towards Open-Search Fact Checking

arXiv: https://arxiv.org/abs/2609.33579 · HTML: https://mlsanity.com/paper/2609.33579/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 32 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Builds on (most cited first, 28 of 28)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [A Survey on Automated Fact-Checking](https://mlsanity.com/paper/2108.11896/) (2021)
- [DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments](https://mlsanity.com/paper/2504.03160/) (2025)
- [FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios](https://mlsanity.com/paper/2307.13528/) (2023)
- [HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification](https://mlsanity.com/paper/2011.03088/) (2020)
- [CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims](https://mlsanity.com/paper/2012.00614/) (2020)
- [WebDancer: Towards Autonomous Information Seeking Agency](https://mlsanity.com/paper/2505.22648/) (2025)
- [MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims](https://mlsanity.com/paper/1909.03242/) (2019)
- [Fact-Checking Complex Claims with Program-Guided Reasoning](https://mlsanity.com/paper/2305.12744/) (2023)
- [AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web](https://mlsanity.com/paper/2305.13117/) (2023)
- [Complex Claim Verification with Evidence Retrieved in the Wild](https://mlsanity.com/paper/2305.11859/) (2023)
- [DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts](https://mlsanity.com/paper/2412.10510/) (2024)
- [FIRE: Fact-checking with Iterative Retrieval and Verification](https://mlsanity.com/paper/2411.00784/) (2024)
- [AmbiFC: Fact-Checking Ambiguous Claims with Evidence](https://mlsanity.com/paper/2104.00640/) (2021)
- [HealthFC: Verifying Health Claims with Evidence-Based Medical Fact-Checking](https://mlsanity.com/paper/2309.08503/) (2023)
- [Generative Large Language Models in Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2407.02351/) (2024)
- [Generating Media Background Checks for Automated Source Critical Reasoning](https://mlsanity.com/paper/2409.00781/) (2024)
- [PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning](https://mlsanity.com/paper/2608.01837/) (2026)
- [Contrastive Learning to Improve Retrieval for Real-world Fact Checking](https://mlsanity.com/paper/2410.04657/) (2024)
- [FactIR: A Real-World Zero-shot Open-Domain Retrieval Benchmark for Fact-Checking](https://mlsanity.com/paper/2502.06006/) (2025)
- [A Benchmark for Open-Domain Numerical Fact-Checking Enhanced by Claim Decomposition](https://mlsanity.com/paper/2510.22055/) (2025)
- [SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward Gating](https://mlsanity.com/paper/2606.07074/) (2026)

## Abstract (arXiv)

Open-search fact checking is not merely retrieval followed by classification, but a sequential decision problem in which every query, source visit, and stopping decision reshapes the evidence available for verification. Yet existing systems often distribute these decisions across predefined pipelines or separately prompted modules rather than learning them as a unified task-specific policy. We introduce OpenFC, a unified verification-policy training framework that post-trains Qwen3-8B as a compact next-action controller over reasoning, evidence acquisition, and stopping. OpenFC learns this policy in two stages. Stepwise-Calibrated Cold Start (SCCS) uses a strong training-time supervisor to review post-initial reasoning, tool-use, and stopping proposals before execution, producing reliable trajectories for supervised fine-tuning without access to gold verdicts. Verification-Aware Reinforcement Learning (VA-RL) then improves the cold-start policy on unresolved claims through budget-aware tool rewards, label-aware advantage reweighting, and localized response masking. Across six fact-checking benchmarks, OpenFC achieves 70.39% average accuracy and 63.30% macro-F1, the highest overall averages among the evaluated methods. Stage-wise ablations further show that SCCS and VA-RL provide complementary gains, supporting the design of the two-stage training framework. These results position OpenFC as a strong and effective framework for open-search fact-checking. We will open-source our code and release the model checkpoints to support reproducibility.