# ReflectFact: Self-Reflective Agents for Improving Comprehension and Reasoning in Multi-Hop Fact Verification

arXiv: https://arxiv.org/abs/2608.12877 · HTML: https://mlsanity.com/paper/2608.12877/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 17 of its 24 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval](https://mlsanity.com/paper/2009.12756/) (2020)
- [Fact-Checking Complex Claims with Program-Guided Reasoning](https://mlsanity.com/paper/2305.12744/) (2023)
- [Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs](https://mlsanity.com/paper/2010.11465/) (2020)
- [Fine-grained Fact Verification with Kernel Graph Attention Network](https://mlsanity.com/paper/1910.09796/) (2019)
- [Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method](https://mlsanity.com/paper/2310.00305/) (2023)
- [Reasoning Over Semantic-Level Graph for Fact Checking](https://mlsanity.com/paper/1909.03745/) (2019)
- [UKP-Athene: Multi-Sentence Textual Entailment for Claim Verification](https://mlsanity.com/paper/1809.01479/) (2018)
- [FaVIQ: FAct Verification from Information-seeking Questions](https://mlsanity.com/paper/2107.02153/) (2021)
- [EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification](https://mlsanity.com/paper/2310.09754/) (2023)
- [Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning](https://mlsanity.com/paper/2212.01060/) (2022)
- [EXPLAIN, EDIT, GENERATE: Rationale-Sensitive Counterfactual Data Augmentation for Multi-hop Fact Verification](https://mlsanity.com/paper/2310.14508/) (2023)
- [CHECKWHY: Causal Fact Verification via Argument Structure](https://mlsanity.com/paper/2408.10918/) (2024)
- [From Verdict to Process: Agentic Reinforcement Learning for Multi-Stage Fact Verification](https://mlsanity.com/paper/2606.13262/) (2026)

## Abstract (arXiv)

Multi-hop fact verification, which verifies claims by reasoning over multiple pieces of evidence, is critical for combating misinformation on social media yet remains highly challenging. Recent methods primarily rely on multi-agent collaboration to decompose fact verification into specialized subtasks. However, these methods face two critical limitations: (1) agents may perform individual subtasks without sufficient awareness of the global verification objective, causing their reasoning to deviate from the intended direction; and (2) conflicts between parametric knowledge and the provided evidence may undermine evidence-grounded reasoning and lead to incorrect verdicts. To address these challenges, we propose ReflectFact, a novel self-reflective agent framework for multi-hop fact verification. ReflectFact introduces three key tasks. Explicit Reasoning Path Planning builds an evidence-grounded reasoning path by resolving implicit entities, decomposing the claim into sub-questions, and integrating the verified facts into a verdict. Evidence-Drift Verification makes the agent re-answer by quoting the supporting evidence when a grounded answer merely echoes its parametric prior, thereby calibrating evidence deviation to ensure grounded comprehension. Reasoning Reflection Verification re-examines each reasoning step and regenerates it once an inconsistency is detected, correcting reasoning flaws such as location bias and replacement bias through a global task perspective. Subsequently, the agent aggregates validated reasoning chains to yield reliable verdicts. Extensive experiments on HOVER and EX-FEVER demonstrate that ReflectFact effectively remedies the comprehension and reasoning defects of existing methods, achieving state-of-the-art performance and respectively outperforming the strongest baseline by 3.32% and 2.78% on the two datasets.