paper-with-me

홈 › Papers

Pessimistic Verification for Open Ended Math Questions

2025-11-26 · Yanxing Huang, Zihan Tang, Zejin Lin, Peng Li, Yang Liu arxiv

Automatic verification is a critical component in building math-solving agents and reinforcement learning, yet it often falls short in generalizability, performance, and cost-efficiency. Identifying that the primary bottleneck of verification lies in error detection capability, we propose pessimistic verification, a paradigm of agentic workflows that rejects a solution if any of multiple parallel verifiers identifies a flaw. We further introduce progressive pessimistic verification, which employs fine-grained proof decomposition to significantly enhance verification accuracy and efficiency. Our approach surpasses the performance and token efficiency of extended long chain-of-thought (long CoT) and mainstream verification workflows, crucially, our analysis reveals that existing benchmarks underestimate its effectiveness on stronger models due to inherent annotation errors. To further validate the effectiveness of our method, we applied a verification-based solving workflow on the IMO 2025 and MathArena Apex 2025 datasets, where the workflow with progressive pessimistic verification exhibits remarkable improvements in both efficiency and accuracy on highly challenging contest-level math problems with state-of-the-art models. Code is available at https://github.com/THUNLP-MT/pverify.

📄 PDF Abstract BibTeX arXiv:2511.21522

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math

2025-10-15 · Shrey Pandit, Austin Xu, Xuan-Phi Nguyen, Yifei Ming 외 arxiv

Large language model (LLM)-based reasoning systems have recently achieved gold medal-level performance in the IMO 2025 competition, writing mathematical proofs where, to receive full credit, each step must be not only co…

Heimdall: test-time scaling on the generative verification

2025-04-14 · Wenlei Shi, Xing Jin

An AI system can create and maintain knowledge only to the extent that it can verify that knowledge itself. Recent work on long Chain-of-Thought reasoning has demonstrated great potential of LLMs on solving competitive p…

Math

Enhancing Large Language Models with Pseudo- and Multisource- Knowledge Graphs for Open-ended Question Answering

2024-02-15 · Jiaxiang Liu, Tong Zhou, Yubo Chen, Kang Liu 외

Mitigating the hallucinations of Large Language Models (LLMs) and enhancing them is a crucial task. Although some existing methods employ model self-enhancement techniques, they fall short of effectively addressing unkno…

Graph GenerationKnowledge GraphsOpen-Ended Question AnsweringQuestion Answering

Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models

2025-02-24 · Alon Albalak, Duy Phung, Nathan Lile, Rafael Rafailov 외

Increasing interest in reasoning models has led math to become a prominent testing ground for algorithmic and methodological improvements. However, existing open math datasets either contain a small collection of high-qu…

GSM8KMathMultiple-choiceReinforcement Learning (RL)

Can Large Language Models Replicate ITS Feedback on Open-Ended Math Questions?

2024-05-10 · Hunter McNichols, Jaewook Lee, Stephen Fancsali, Steve Ritter 외

Intelligent Tutoring Systems (ITSs) often contain an automated feedback component, which provides a predefined feedback message to students when they detect a predefined error. To such a feedback component, we often reso…

Mathtext similarity