Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Ante, Song, Linfeng, Tian, Ye, Yu, Dian, Mi, Haitao, Duan, Xiangyu, Tu, Zhaopeng, Su, Jinsong, Yu, Dong
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

LiteSearch: Efficacious Tree Search for LLM
di: Wang, Ante, et al.
Pubblicazione: (2024)

Self-Consistency Boosts Calibration for Math Reasoning
di: Wang, Ante, et al.
Pubblicazione: (2024)

Fine-Grained Self-Endorsement Improves Factuality and Reasoning
di: Wang, Ante, et al.
Pubblicazione: (2024)

Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains
di: Su, Yi, et al.
Pubblicazione: (2025)

Teaching LLMs to Refine with Tools
di: Yu, Dian, et al.
Pubblicazione: (2024)

SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models
di: Yu, Dian, et al.
Pubblicazione: (2024)

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models
di: Dai, Runpeng, et al.
Pubblicazione: (2025)

Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
di: Tian, Ye, et al.
Pubblicazione: (2024)

DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
di: Yue, Murong, et al.
Pubblicazione: (2024)

Response Enhanced Semi-supervised Dialogue Query Generation
di: Huang, Jianheng, et al.
Pubblicazione: (2023)

DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
di: Zhang, Ziyin, et al.
Pubblicazione: (2025)

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

Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values
di: Yu, Dian, et al.
Pubblicazione: (2025)

Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
di: Li, Yansi, et al.
Pubblicazione: (2025)

Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
di: Zhang, Yuheng, et al.
Pubblicazione: (2025)

Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning
di: Liang, Zhenwen, et al.
Pubblicazione: (2025)

Don't Get Stuck: A Deadlock Recovery Approach
di: Baldini, Francesca, et al.
Pubblicazione: (2024)

Don't Get Too Excited -- Eliciting Emotions in LLMs
di: Fazzi, Gino Franco, et al.
Pubblicazione: (2025)

When Sourcing Donors, Don't Get in a Rut
Pubblicazione: (2024)

Rectify, Don't Regret: Avoiding Pitfalls of Differentiable Simulation in Trajectory Prediction
di: Yadav, Harsh, et al.
Pubblicazione: (2026)

Don't despair, not today
di: Zhaohui Su
Pubblicazione: (2025)

Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
di: Wang, Xiyao, et al.
Pubblicazione: (2024)

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
di: Chen, Xingyu, et al.
Pubblicazione: (2024)

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
di: Wang, Yue, et al.
Pubblicazione: (2025)

Don't Get Left Behind: Moving Library Instruction Online
di: Hillman, Christina R., et al.
Pubblicazione: (2016)

Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
di: Shi, Yucheng, et al.
Pubblicazione: (2026)

Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty
di: Ren, Jingyi, et al.
Pubblicazione: (2026)

Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
di: Zhou, Jin Peng, et al.
Pubblicazione: (2024)

Don't Miss the Forest for the Trees: How Abstracting Nature Can Get Us Closer to Our Goals
di: Jake Lawlor
Pubblicazione: (2025)

Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning
di: Liu, Rui, et al.
Pubblicazione: (2025)

Reasoning Models Reason Well, Until They Don't
di: Rameshkumar, Revanth, et al.
Pubblicazione: (2025)

Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning
di: Liu, Haolin, et al.
Pubblicazione: (2026)

Group Distributionally Robust Optimization-Driven Reinforcement Learning for LLM Reasoning
di: Panaganti, Kishan, et al.
Pubblicazione: (2026)

Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
di: Zhang, Yuheng, et al.
Pubblicazione: (2024)

On the Information Redundancy in Non-Autoregressive Translation
di: Wang, Zhihao, et al.
Pubblicazione: (2024)

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
di: Hassid, Michael, et al.
Pubblicazione: (2025)

Love Don't Need a Reason
di: Jones, Matthew J.
Pubblicazione: (2020)

One Token to Fool LLM-as-a-Judge
di: Zhao, Yulai, et al.
Pubblicazione: (2025)

CLUE: Non-parametric Verification from Experience via Hidden-State Clustering
di: Liang, Zhenwen, et al.
Pubblicazione: (2025)

HunyuanProver: A Scalable Data Synthesis Framework and Guided Tree Search for Automated Theorem Proving
di: Li, Yang, et al.
Pubblicazione: (2024)