Reasoning Verification

Follow this topic Ask about this topic

Reasoning verification studies how to detect flawed steps, assess proof validity, and determine whether answers follow from evidence rather than merely matching an answer key. Approaches include process reward models and step classifiers, self- or multi-agent checking, symbolic and formal proof checkers, and evidence-grounded tools for tasks such as mathematics, code, and multi-hop fact verification. Benchmarks increasingly test first-error localization, robustness to valid but non-canonical solutions, and whether a verifier depends on the evidence it is given. A central challenge is balancing reliable detection against false rejection, reward hacking, and the token or human-review costs of stronger checks.

Latest papers

57 papers9 papers in the last four weeks, up 80% on the four weeks before. 0.1% of all new papers.

An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models
May 31, 2026Mingzhong Sun, Teresa Yeo, Armando Solar-Lezama +1Reasoning Evaluation LLM Interpretability
1NUS Department of Computer Science · 4Singapore-MIT Alliance for Research and Technology (SMART) · 2MIT EECS +1
Self-Trained Verification for Training- and Test-Time Self-Improvement
May 28, 2026Chen Henry Wu, Aditi RaghunathanLLM Self-Refinement Language Model Self-Improvement
Carnegie Mellon University
Conformal Certification of Reasoning Trace Prefixes
May 28, 2026Matt Y. Cheung, Ashok Veeraraghavan, Hanjie Chen +1Conformal Prediction Language Model Calibration
Department of Electrical & Computer Engineering, Rice University · Department of Computer Science, Rice University
Debate Helps Weak Judges Reward Stronger Models
May 26, 2026Ethan Elasky, Frank Nakasako, Naman GoyalScalable Oversight LLM-as-a-Judge
Palaestra Research · Independent
The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering
May 20, 2026Yefan Zhou, Yilun Zhou, Austin Xu +3Language Model Steering Activation Steering
Dartmouth College · Datadog AI Research · Salesforce AI Research
Using Aristotle API for AI-Assisted Theorem Proving in Lean 4: A Formalisation Case Study of the Grasshopper Problem
May 19, 2026Gabriel Rongyang LauMathematical Reasoning Lean Theorem Proving
Nanyang Technological University, Singapore
A Nash Equilibrium Framework For Training-Free Multimodal Step Verification
May 19, 2026Rohit Sinha, Kunal Tilaganji, Tanuja Ganu +3Multi-View Consistency Game Theory
1Microsoft Research India · 2Indian Institute of Technology Hyderabad
Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains
May 18, 2026Zhonghang Yuan, Zhefan Wang, Fang Hu +7RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards
Shanghai Artificial Intelligence Laboratory · Shanghai Innovation Institute
Unsupervised Process Reward Models
May 11, 2026Artyom Gadetsky, Maxim Kodryan, Siba Smarak Panigrahi +2Reward Modeling Process Reward Models
Swiss Federal Institute of Technology (EPFL)
LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification
May 8, 2026Xuan Li, Yining Wang, Yuchen Liu +7CoT Reasoning Efficient Language Model Reasoning
University of Science and Technology of China · Unisound AI Technology Co., Ltd · MAIS, Institute of Automation, Chinese Academy of Sciences
Verifiable Counterfactual Supervision for Process Reward Models
May 4, 2026Yinghui Chi, Yuanhong WangProcess Reward Models Process Supervision
Jilin University
Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization
May 2, 2026Yunhan Bu, Quan Zhang, Huaping Zhang +9Structural Causal Models RL for Language Model Reasoning
Beijing Institute of Technology, Beijing, China · School of Computer Science and Technology, Xinjiang University, Urumqi, China · Military Science Information Research Center, Academy of Military Science, Beijing, China
Navigating the Conceptual Multiverse
Apr 20, 2026Andre Ye, Jenny Y. Huang, Alicia Guo +3LLM Decision-Making Human-AI Decision Making
MIT EECS · UW Allen School of CSE · UW Department of Philosophy
Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models
Apr 17, 2026Jiaoyang Ruan, Xin Gao, Yinda Chen +5Diffusion Model Alignment Diffusion Language Model Inference
Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China · University of Science and Technology of China, Hefei, China +1
Toward Explanatory Equilibrium: Verifiable Reasoning as a Coordination Mechanism under Asymmetric Information
Apr 10, 2026Feliks Bańka, Jarosław A. ChudziakMulti-Agent LLM Systems Multi-Agent Coordination
The Faculty of Electronics and Information Technology, Warsaw University of Technology, Warsaw, Poland
Case-Grounded Evidence Verification: A Framework for Constructing Evidence-Sensitive Supervision
Apr 10, 2026Soroosh Tayebi Arasteh, Mehdi Joodaki, Mahshad Lotfinia +2Evidence-Grounded Reasoning Reasoning Verification
RWTH Aachen University, Aachen, Germany
ProofSketcher: Hybrid LLM + Lightweight Proof Checker for Reliable Math/Logic Reasoning
Apr 7, 2026Kranthi Kommuru, Kunal Khanvilkar, Gaurav ParekhLarge Language Model-Guided Theorem Proving Automated Theorem Proving
Automatic Data Processing, Inc Atlanta, USA · Amazon Web Services, Inc Banglore, India
Do We Need Frontier Models to Verify Mathematical Proofs?
Apr 2, 2026Aaditya Naik, Guruprerana Shabadi, Rajeev Alur +1LLM Input Optimization Reasoning Verification
University of Pennsylvania, U.S.A.
ORACLE: Optimizing Reasoning Abilities of Large Language Models via Constraint-Led Synthetic Data Elicitation
Mar 22, 2026Zhuojie Yang, Wentao Wan, Keze WangSynthetic Data Generation for Language Models LLM Reasoning
School of Computer Science and Engineering, Sun Yat-sen University
Towards Verifiable AI with Lightweight Cryptographic Proofs of Inference
Mar 19, 2026Pranay Anchuri, Matteo Campanelli, Paul Cesaretti +4Verifiable Outsourced Computation Neural Network Verification
Offchain Labs · University of Tartu, Estonia · CUNY Graduate Center +1
Measuring Progress in Reasoning Toward Mathematical Discovery with Automatic Verification
Mar 16, 2026Erik Y. Wang, Sumeet R. Motwani, James V. Roggeveen +9Mathematical Reasoning Benchmarks LLM Mathematical Reasoning
Stanford University · Benchmark · University of Oxford +3
MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
Mar 16, 2026MiroMind Team, S. Bai, L. Bing +41Autonomous Research Agents Long-Horizon LLM Agents
One-Token Verification for Reasoning Correctness Estimation
Mar 1, 2026Zhan Zhuang, Xiequn Wang, Zebin Chen +4Reasoning Verification LLM Reasoning
Southern University of Science and Technology, Shenzhen, China · City University of Hong Kong, Hong Kong SAR · Zhejiang University, Hangzhou, China
Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models
Feb 20, 2026Rishabh Tiwari, Aditya Tomar, Udbhav Bamba +5Process Reward Models Reward Hacking
UC Berkeley · Transmute AI · ICSI +1
When to Trust the Cheap Check: Weak and Strong Verification for Reasoning
Feb 19, 2026Shayan Kiyani, Sima Noorani, George Pappas +1LLM Answer Verification Reasoning Verification
University of Pennsylvania
Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge
Feb 10, 2026Wei Yang, Shixuan Li, Heng Ping +3LLM Auditing Preference Optimization
University of Southern California
The Bidirectional Process Reward Model
Aug 3, 2025Lingyin Zhang, Jun Gao, Xiaoxue Ren +1Process Reward Models Reasoning Verification
School of Computer Science and Technology, Soochow University · Biomedical Basic Research Center of Jiangsu, Soochow University, Suzhou, Jiangsu 215123, China · School of Software Technology, Zhejiang University +1

May 31, 2026J/K move · Enter open · S save

An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models

Mingzhong Sun, Teresa Yeo, Armando Solar-Lezama, Tan Zhi-Xuan

1NUS Department of Computer Science · 4Singapore-MIT Alliance for Research and Technology (SMART) · 2MIT EECS+1

Reasoning Evaluation LLM Interpretability Large Reasoning Models Reasoning Verification

Open paper AskPDF arXiv

Studies of human reasoning have shown that people are typically stronger at evaluating reasoning than producing it from scratch. In contrast, large reasoning models (LRMs) are trained to excel at producing long chains of reasoning to solve complex problems. How then do LRMs perform at evaluating reasons? We investigate this with the Valid-Answer-Invalid-Reasoning (VAIR) dataset: math problems and solutions with trivial reasoning flaws but valid answers, designed to isolate reasoning evaluation from the confound of reasoning production. Unlike humans, who we find are only 6% worse at grading than solving such problems, we find a substantial production-evaluation gap in LRMs: frontier models score as low as 48% when evaluating VAIR solutions, despite near-perfect solution production. Why this enigma? Through chain-of-thought (CoT) analysis, we find evidence of an answer confirmation bias: LRMs often produce then check for the correct answer instead of carefully verifying each step, fabricating rationalizations even when noticing anomalous reasoning. Linear probes corroborate this, showing that while LRM activations encode some representation of valid reasoning, they fail to robustly represent VAIR solutions as invalid. Causal patching of the final answer's representations causes LRM verdicts and activations to flip, demonstrating that answer validity is responsible for models' confirmation biases. These findings indicate an outstanding limitation in dominant approaches to reasoning training, which incentivize LRMs to produce and confirm reasoning towards correct answers, but not to robustly evaluate the underlying reasons.