Copertina

STeCa: Step-level Trajectory Calibration for LLM Agent Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Hanlin, Wang, Jian, Leong, Chak Tou, Li, Wenjie
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

E2CL: Exploration-based Error Correction Learning for Embodied Agents
di: Wang, Hanlin, et al.
Pubblicazione: (2024)

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

Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents
di: Wang, Hanlin, et al.
Pubblicazione: (2026)

Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models
di: Wang, Jian, et al.
Pubblicazione: (2025)

Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models
di: Liu, Youwei, et al.
Pubblicazione: (2026)

Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region
di: Leong, Chak Tou, et al.
Pubblicazione: (2025)

TokenSkip: Controllable Chain-of-Thought Compression in LLMs
di: Xia, Heming, et al.
Pubblicazione: (2025)

Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement
di: Xiong, Weimin, et al.
Pubblicazione: (2024)

Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue
di: Wang, Jian, et al.
Pubblicazione: (2024)

COMAP: Co-Evolving World Models and Agent Policies for LLM Agents
di: Liu, Youwei, et al.
Pubblicazione: (2026)

Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering
di: Leong, Chak Tou, et al.
Pubblicazione: (2026)

Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
di: Deng, Yihe, et al.
Pubblicazione: (2025)

LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
di: Sun, Lihao, et al.
Pubblicazione: (2026)

A Study on the Calibration of In-context Learning
di: Zhang, Hanlin, et al.
Pubblicazione: (2023)

Offline Reinforcement Learning for LLM Multi-Step Reasoning
di: Wang, Huaijie, et al.
Pubblicazione: (2024)

Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents
di: Song, Yifan, et al.
Pubblicazione: (2024)

StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason
di: Zhang, Kaiyi, et al.
Pubblicazione: (2025)

Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting
di: Xia, Heming, et al.
Pubblicazione: (2025)

TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration
di: Du, Yuwei, et al.
Pubblicazione: (2024)

Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation
di: Zhao, Anhao, et al.
Pubblicazione: (2026)

ATLaS: Agent Tuning via Learning Critical Steps
di: Chen, Zhixun, et al.
Pubblicazione: (2025)

CaRT: Teaching LLM Agents to Know When They Know Enough
di: Liu, Grace, et al.
Pubblicazione: (2025)

Induction Head Toxicity Mechanistically Explains Repetition Curse in Large Language Models
di: Wang, Shuxun, et al.
Pubblicazione: (2025)

TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents
di: Djuhera, Aladin, et al.
Pubblicazione: (2026)

RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
di: Wang, Zihan, et al.
Pubblicazione: (2025)

On the Limitations of Language Targeted Pruning: Investigating the Calibration Language Impact in Multilingual LLM Pruning
di: Kurz, Simon, et al.
Pubblicazione: (2024)

Federated In-Context LLM Agent Learning
di: Wu, Panlong, et al.
Pubblicazione: (2024)

SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
di: Yu, Zhuoyun, et al.
Pubblicazione: (2026)

Encoding Agent Trajectories as Representations with Sequence Transformers
di: Tsiligkaridis, Athanasios, et al.
Pubblicazione: (2024)

TIER: Trajectory-Invariant Execution Rewards for Multi-Step Tool Composition
di: Kulkarni, Anay, et al.
Pubblicazione: (2026)

EMSEdit: Efficient Multi-Step Meta-Learning-based Model Editing
di: Li, Xiaopeng, et al.
Pubblicazione: (2025)

BAGEN: Are LLM Agents Budget-Aware?
di: Lin, Yuxiang, et al.
Pubblicazione: (2026)

LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning
di: Huang, Wei, et al.
Pubblicazione: (2026)

Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting
di: Hu, Michael Y., et al.
Pubblicazione: (2025)

MPO: Boosting LLM Agents with Meta Plan Optimization
di: Xiong, Weimin, et al.
Pubblicazione: (2025)

Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
di: Monsefi, Amin Karimi, et al.
Pubblicazione: (2026)

ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering
di: Liu, Zexi, et al.
Pubblicazione: (2025)

R$^2$PO: Decoupling Training Trajectories from Inference Responses for LLM Reasoning
di: Wang, Jingchu, et al.
Pubblicazione: (2026)

SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translation
di: Yang, Wenjie, et al.
Pubblicazione: (2025)

AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
di: Lù, Xing Han, et al.
Pubblicazione: (2025)