Lune

EMNLP Findings2025

VerifiAgent: a Unified Verification Agent in Language Model Reasoning

Jiuzhou Han, Wray L. Buntine, Ehsan Shareghi

Abstract

Large language models demonstrate remarkable reasoning capabilities but often produce unreliable or incorrect responses. Existing verification methods are typically model-specific or domain-restricted, requiring significant computational resources and lacking scalability across diverse reasoning tasks. To address these limitations, we propose VerifiAgent, a unified verification agent that integrates two levels of verification: meta-verification, which assesses completeness and consistency in model responses, and tool-based adaptive verification, where Ver-ifiAgent autonomously selects appropriate verification tools based on the reasoning type, including mathematical, logical, or commonsense reasoning. This adaptive approach ensures both efficiency and robustness across different verification scenarios. Experimental results show that VerifiAgent outperforms baseline verification methods (e.g., deductive verifier, backward verifier) among all reasoning tasks. Additionally, it can further enhance reasoning accuracy by leveraging feedback from verification results. VerifiAgent can also be effectively applied to inference scaling, achieving better results with fewer generated samples and costs compared to existing process reward models in the mathematical reasoning domain. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Chain-of-Verification Reduces Hallucination in Large Language Models cites Deductive Verification of Chain-of-Thought Reasoning
  • CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing cites LEVER: Learning to Verify Language-to-Code Generation with Execution
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Can Dependencies Induced by LLM-Agent Workflows Be Trusted?Yu Yao, Yiliao Song, Yian Xie, Mengdan Fan et al.NeurIPS 2025 · 4 citations

Builds on14

  1. Let's Verify Step by StepHunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards et al.ICLR 2024 · 3,045 citations
  2. CRITIC: Large Language Models Can Self-Correct with Tool-Interactive CritiquingZhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen et al.ICLR 2024 · 699 citations
  3. LEVER: Learning to Verify Language-to-Code Generation with ExecutionAnsong Ni, Srini Iyer, Dragomir Radev, Veselin Stoyanov et al.ICML 2023 · 318 citations
  4. Chain-of-Verification Reduces Hallucination in Large Language ModelsShehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu et al.ACL Findings 2024 · 281 citations
  5. Deductive Verification of Chain-of-Thought ReasoningZhan Ling, Yunhao Fang, Xuanlin Li, Zhiao Huang et al.NeurIPS 2023 · 234 citations

Related papers

  1. Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to DeliberationZhiwei Zhang, Xiaomin Li, Yudi Lin, Hui Liu et al.ICLR 2026 · 13 citations
  2. RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable EnvironmentsZhiyuan Zeng, Hamish Ivison, Yiping Wang, Lifan Yuan et al.ICML 2026 · 28 citations
  3. Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning ModelsZhiyuan Hu, Yibo Wang, Hanze Dong, Yuhui Xu et al.ACL Findings 2026 · 1 citation
  4. Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative VerifierJianyuan Zhong, Zeju Li, Zhijian Xu, Xiangyu Wen et al.ACL 2026 · 3 citations
  5. PAT-Agent: Autoformalization for Model CheckingXinyue Zuo, Yifan Zhang, Hongshu Wang, Yufan Cai et al.ASE 2025 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines