Copertina

Step-Wise Formal Verification for LLM-Based Mathematical Problem Solving

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhou, Kuo, Zhang, Lu
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

StepMathAgent: A Step-Wise Agent for Evaluating Mathematical Processes through Tree-of-Error
di: Yang, Shu-Xun, et al.
Pubblicazione: (2025)

Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification
di: Liu, Chengwu, et al.
Pubblicazione: (2025)

Propose, Solve, Verify: Self-Play Through Formal Verification
di: Wilf, Alex, et al.
Pubblicazione: (2025)

Conjecturing: An Overlooked Step in Formal Mathematical Reasoning
di: Sivakumar, Jasivan Alex, et al.
Pubblicazione: (2025)

FormalGeo: An Extensible Formalized Framework for Olympiad Geometric Problem Solving
di: Zhang, Xiaokai, et al.
Pubblicazione: (2023)

Tool-Augmented Hybrid Ensemble Reasoning with Distillation for Bilingual Mathematical Problem Solving
di: Lu, Peiqing, et al.
Pubblicazione: (2025)

Formally Solving Answer-Construction Problems in Lean
di: Sun, Jialiang, et al.
Pubblicazione: (2025)

Expected Value Alignment for Generative Reward Modeling in Formal Mathematics Verification
di: Ji, Shihao, et al.
Pubblicazione: (2026)

The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering
di: Zhou, Yefan, et al.
Pubblicazione: (2026)

Learning to Generate Formally Verifiable Step-by-Step Logic Reasoning via Structured Formal Intermediaries
di: Chen, Luoxin, et al.
Pubblicazione: (2026)

Agentic LLM Planning via Step-Wise PDDL Simulation: An Empirical Characterisation
di: Göbel, Kai, et al.
Pubblicazione: (2026)

When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning
di: Singhi, Nishad, et al.
Pubblicazione: (2025)

TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision
di: Zhou, Ruiwen, et al.
Pubblicazione: (2024)

Solving Formal Math Problems by Decomposition and Iterative Reflection
di: Zhou, Yichi, et al.
Pubblicazione: (2025)

RM-PoT: Reformulating Mathematical Problems and Solving via Program of Thoughts
di: Zhang, Yu, et al.
Pubblicazione: (2025)

Is Mathematical Problem-Solving Expertise in Large Language Models Associated with Assessment Performance?
di: Zhang, Liang, et al.
Pubblicazione: (2026)

Plan before Solving: Problem-Aware Strategy Routing for Mathematical Reasoning with LLMs
di: Qi, Shihao, et al.
Pubblicazione: (2025)

Exploring Communication Strategies for Collaborative LLM Agents in Mathematical Problem-Solving
di: Zhang, Liang, et al.
Pubblicazione: (2025)

Solving Math Word Problems Using Estimation Verification and Equation Generation
di: Piehl, Mitchell, et al.
Pubblicazione: (2025)

Formalizing Mathematics at Scale
di: Rammal, Ahmad, et al.
Pubblicazione: (2026)

Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
di: Didolkar, Aniket, et al.
Pubblicazione: (2024)

Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving
di: Xu, Xin, et al.
Pubblicazione: (2025)

Preference Elicitation for Step-Wise Explanations in Logic Puzzles
di: Foschini, Marco, et al.
Pubblicazione: (2025)

DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving
di: Tong, Yuxuan, et al.
Pubblicazione: (2024)

Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving
di: Gao, Songyang, et al.
Pubblicazione: (2025)

Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solving
di: Mai, Xinji, et al.
Pubblicazione: (2025)

NCV: A Node-Wise Consistency Verification Approach for Low-Cost Structured Error Localization in LLM Reasoning
di: Zhang, Yulong, et al.
Pubblicazione: (2025)

AutoGPS: Automated Geometry Problem Solving via Multimodal Formalization and Deductive Reasoning
di: Ping, Bowen, et al.
Pubblicazione: (2025)

SMART: Self-Generating and Self-Validating Multi-Dimensional Assessment for LLMs' Mathematical Problem Solving
di: Hou, Yujie, et al.
Pubblicazione: (2025)

Solving Probabilistic Verification Problems of Neural Networks using Branch and Bound
di: Boetius, David, et al.
Pubblicazione: (2024)

STELLAR: Structure-guided LLM Assertion Retrieval and Generation for Formal Verification
di: Rajabi, Saeid, et al.
Pubblicazione: (2025)

TrustGeoGen: Formal-Verified Data Engine for Trustworthy Multi-modal Geometric Problem Solving
di: Fu, Daocheng, et al.
Pubblicazione: (2025)

Tracing Mathematical Proficiency Through Problem-Solving Processes
di: Park, Jungyang, et al.
Pubblicazione: (2025)

Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Tools
di: Hao, Yilun, et al.
Pubblicazione: (2024)

Cross-Problem Learning for Solving Vehicle Routing Problems
di: Lin, Zhuoyi, et al.
Pubblicazione: (2024)

FGeo-HyperGNet: Geometric Problem Solving Integrating FormalGeo Symbolic System and Hypergraph Neural Network
di: Zhang, Xiaokai, et al.
Pubblicazione: (2024)

Mathify: Evaluating Large Language Models on Mathematical Problem Solving Tasks
di: Anand, Avinash, et al.
Pubblicazione: (2024)

Learning to Solve Compositional Geometry Routing Problems
di: Fan, Mingfeng, et al.
Pubblicazione: (2026)

Textual and Visual Prompt Fusion for Image Editing via Step-Wise Alignment
di: Feng, Zhanbo, et al.
Pubblicazione: (2023)

PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving
di: Parmar, Mihir, et al.
Pubblicazione: (2025)