Stepwise Informativeness Search for Efficient and Effective LLM Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Siyuan, Zhao, Enda, Wei, Zhongyu, Ren, Xiang
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

Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs
di: Wang, Siyuan, et al.
Pubblicazione: (2024)

Symbolic Working Memory Enhances Language Models for Complex Rule Application
di: Wang, Siyuan, et al.
Pubblicazione: (2024)

Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation
di: Wang, Siyuan, et al.
Pubblicazione: (2024)

Segment-Level Attribution for Selective Learning of Long Reasoning Traces
di: Wang, Siyuan, et al.
Pubblicazione: (2026)

HyLaT: Efficient Multi-Agent Communication via Hybrid Latent-Text Protocol
di: Mou, Xinyi, et al.
Pubblicazione: (2026)

SpeechMedAssist: Efficiently and Effectively Adapting Speech Language Models for Medical Consultation
di: Chen, Sirry, et al.
Pubblicazione: (2026)

Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning
di: Lee, Sangmook, et al.
Pubblicazione: (2025)

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs
di: Ding, Xuanwen, et al.
Pubblicazione: (2025)

Interleaved Latent Visual Reasoning with Selective Perceptual Modeling
di: Dong, Shuai, et al.
Pubblicazione: (2025)

EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation
di: Mou, Xinyi, et al.
Pubblicazione: (2025)

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

Rethinking Stepwise Model Routing: A Cost-Efficient Table Reasoning Perspective
di: Ye, Shenghao, et al.
Pubblicazione: (2026)

Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning
di: Lu, Zimu, et al.
Pubblicazione: (2024)

StepWiser: Stepwise Generative Judges for Wiser Reasoning
di: Xiong, Wei, et al.
Pubblicazione: (2025)

Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks
di: Yue, Shengbin, et al.
Pubblicazione: (2024)

From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking
di: Wang, Siyuan, et al.
Pubblicazione: (2024)

Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
di: Li, Xintong, et al.
Pubblicazione: (2026)

Strong Reasoning Isn't Enough: Evaluating Evidence Elicitation in Interactive Diagnosis
di: Long, Zhuohan, et al.
Pubblicazione: (2026)

Enhancing Mathematical Reasoning in LLMs by Stepwise Correction
di: Wu, Zhenyu, et al.
Pubblicazione: (2024)

R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning
di: Zhao, Qingfei, et al.
Pubblicazione: (2025)

Unifying Tree Search Algorithm and Reward Design for LLM Reasoning: A Survey
di: Wei, Jiaqi, et al.
Pubblicazione: (2025)

Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoning
di: Wang, Zezhong, et al.
Pubblicazione: (2025)

The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning
di: Zhu, Xinyu, et al.
Pubblicazione: (2025)

Scaling Search-Augmented LLM Reasoning via Adaptive Information Control
di: Xiong, Siheng, et al.
Pubblicazione: (2026)

In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search
di: Li, Huihan, et al.
Pubblicazione: (2023)

Improving Reasoning Capabilities in Small Models through Mixture-of-Layers Distillation with Stepwise Attention on Key Information
di: Chen, Yao, et al.
Pubblicazione: (2026)

PCRLLM: Proof-Carrying Reasoning with Large Language Models under Stepwise Logical Constraints
di: Li, Tangrui, et al.
Pubblicazione: (2025)

Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization
di: Wang, Liang, et al.
Pubblicazione: (2026)

SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution
di: Wang, Hanlin, et al.
Pubblicazione: (2025)

Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models
di: Cui, Yingqian, et al.
Pubblicazione: (2025)

DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference
di: Liu, Xiang, et al.
Pubblicazione: (2025)

Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents
di: Shi, Yaorui, et al.
Pubblicazione: (2025)

DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning
di: Wu, Yuanhao, et al.
Pubblicazione: (2025)

SGR: A Stepwise Reasoning Framework for LLMs with External Subgraph Generation
di: Zhang, Xin, et al.
Pubblicazione: (2026)

Stepwise Self-Consistent Mathematical Reasoning with Large Language Models
di: Zhao, Zilong, et al.
Pubblicazione: (2024)

OViP: Online Vision-Language Preference Learning for VLM Hallucination
di: Liu, Shujun, et al.
Pubblicazione: (2025)

Boosting LLM's Molecular Structure Elucidation with Knowledge Enhanced Tree Search Reasoning
di: Zhuang, Xiang, et al.
Pubblicazione: (2025)

StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning
di: Wang, Hao, et al.
Pubblicazione: (2026)

Enhancing LLM Reasoning with Reward-guided Tree Search
di: Jiang, Jinhao, et al.
Pubblicazione: (2024)

CommunityBench: Benchmarking Community-Level Alignment across Diverse Groups and Tasks
di: Lin, Jiayu, et al.
Pubblicazione: (2026)