Scaling Flaws of Verifier-Guided Search in Mathematical Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yu, Fei, Li, Yingru, Wang, Benyou
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Robust Search with Uncertainty-Aware Value Models for Language Model Reasoning
di: Yu, Fei, et al.
Pubblicazione: (2025)

OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning
di: Yu, Fei, et al.
Pubblicazione: (2023)

MathScale: Scaling Instruction Tuning for Mathematical Reasoning
di: Tang, Zhengyang, et al.
Pubblicazione: (2024)

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
di: He, Zhiwei, et al.
Pubblicazione: (2025)

FindTheFlaws: Annotated Errors for Detecting Flawed Reasoning and Scalable Oversight Research
di: Recchia, Gabriel, et al.
Pubblicazione: (2025)

SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation
di: Nezhad, Sina Bagheri, et al.
Pubblicazione: (2025)

xVerify: Efficient Answer Verifier for Reasoning Model Evaluations
di: Chen, Ding, et al.
Pubblicazione: (2025)

LLMs for Mathematical Modeling: Towards Bridging the Gap between Natural and Mathematical Languages
di: Huang, Xuhan, et al.
Pubblicazione: (2024)

PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering
di: Wang, Xiangfeng, et al.
Pubblicazione: (2026)

Guided Verifier: Collaborative Multimodal Reasoning via Dynamic Process Supervision
di: Sun, Lingzhuang, et al.
Pubblicazione: (2026)

InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling
di: Li, Peiji, et al.
Pubblicazione: (2025)

Verifier-Backed Hard Problem Generation for Mathematical Reasoning
di: Lai, Yuhang, et al.
Pubblicazione: (2026)

Examining False Positives under Inference Scaling for Mathematical Reasoning
di: Wang, Yu, et al.
Pubblicazione: (2025)

Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
di: Chen, Jiangjie, et al.
Pubblicazione: (2025)

Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical Reasoning
di: Deng, Jie, et al.
Pubblicazione: (2026)

Progressive Mastery: Customized Curriculum Learning with Guided Prompting for Mathematical Reasoning
di: Wu, Muling, et al.
Pubblicazione: (2025)

rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset
di: Liu, Yifei, et al.
Pubblicazione: (2025)

BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search
di: Sun, Linzhuang, et al.
Pubblicazione: (2024)

QFFT, Question-Free Fine-Tuning for Adaptive Reasoning
di: Liu, Wanlong, et al.
Pubblicazione: (2025)

DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning
di: Shao, Zhihong, et al.
Pubblicazione: (2025)

Model Unlearning via Sparse Autoencoder Subspace Guided Projections
di: Wang, Xu, et al.
Pubblicazione: (2025)

ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning
di: Pei, Qizhi, et al.
Pubblicazione: (2025)

Toward Automated Robustness Evaluation of Mathematical Reasoning
di: Hou, Yutao, et al.
Pubblicazione: (2025)

Evaluating the Role of Verifiers in Test-Time Scaling for Legal Reasoning Tasks
di: Romano, Davide, et al.
Pubblicazione: (2025)

Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning
di: Son, Guijin, et al.
Pubblicazione: (2025)

Entropy-Guided Reasoning Compression
di: Zhu, Hourun, et al.
Pubblicazione: (2025)

Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning
di: Cao, Lang, et al.
Pubblicazione: (2024)

Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection
di: Ahuja, Kabir, et al.
Pubblicazione: (2025)

PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts
di: Wang, Yiming, et al.
Pubblicazione: (2025)

BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving
di: Wang, Teng, et al.
Pubblicazione: (2024)

Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws
di: Jha, Akshita, et al.
Pubblicazione: (2024)

Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
di: Setlur, Amrith, et al.
Pubblicazione: (2024)

From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling
di: Chen, Zhengyu, et al.
Pubblicazione: (2025)

Review of Inference-Time Scaling Strategies: Reasoning, Search and RAG
di: Wang, Zhichao, et al.
Pubblicazione: (2025)

The Flaw of Averages: Quantifying Uniformity of Performance on Benchmarks
di: Uzunoglu, Arda, et al.
Pubblicazione: (2025)

CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents
di: Tang, Yihong, et al.
Pubblicazione: (2026)

Reinforcing General Reasoning without Verifiers
di: Zhou, Xiangxin, et al.
Pubblicazione: (2025)

SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
di: Liu, Junteng, et al.
Pubblicazione: (2025)

How We Refute Claims: Automatic Fact-Checking through Flaw Identification and Explanation
di: Kao, Wei-Yu, et al.
Pubblicazione: (2024)

LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback
di: Gao, Bofei, et al.
Pubblicazione: (2024)