Cover Image

Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xiong, Weimin, Song, Yifan, Zhao, Xiutian, Wu, Wenhao, Wang, Xun, Wang, Ke, Li, Cheng, Peng, Wei, Li, Sujian
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories
by: Song, Yifan, et al.
Published: (2024)

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

More Vulnerable than You Think: On the Stability of Tool-Integrated LLM Agents
by: Xiong, Weimin, et al.
Published: (2025)

An Electoral Approach to Diversify LLM-based Multi-Agent Collective Decision-Making
by: Zhao, Xiutian, et al.
Published: (2024)

ORCHID: A Chinese Debate Corpus for Target-Independent Stance Detection and Argumentative Dialogue Summarization
by: Zhao, Xiutian, et al.
Published: (2024)

Measuring the Inconsistency of Large Language Models in Preferential Ranking
by: Zhao, Xiutian, et al.
Published: (2024)

Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQL
by: Dai, Yaxun, et al.
Published: (2026)

STEVE Series: Step-by-Step Construction of Agent Systems in Minecraft
by: Zhao, Zhonghan, et al.
Published: (2024)

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

Enhancing Decision-Making for LLM Agents via Step-Level Q-Value Models
by: Zhai, Yuanzhao, et al.
Published: (2024)

SRR-Judge: Step-Level Rating and Refinement for Enhancing Search-Integrated Reasoning in Search Agents
by: Zhang, Chen, et al.
Published: (2026)

PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
by: Zhu, Dawei, et al.
Published: (2023)

Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding
by: Huang, An, et al.
Published: (2026)

Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents
by: Yang, Ruihan, et al.
Published: (2026)

AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress
by: Xi, Zhiheng, et al.
Published: (2025)

Highlight Every Step: Knowledge Distillation via Collaborative Teaching
by: Zhao, Haoran, et al.
Published: (2019)

Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs
by: Li, Qi, et al.
Published: (2025)

Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning
by: Li, Pengxiang, et al.
Published: (2025)

CoUDA: Coherence Evaluation via Unified Data Augmentation
by: Zhu, Dawei, et al.
Published: (2024)

Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents
by: Zhen, Shuai, et al.
Published: (2026)

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

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement
by: Zhang, Yueke, et al.
Published: (2025)

EERPD: Leveraging Emotion and Emotion Regulation for Improving Personality Detection
by: Li, Zheng, et al.
Published: (2024)

Verified Critical Step Optimization for LLM Agents
by: Li, Mukai, et al.
Published: (2026)

Discovering Process-Outcome Credit in Multi-Step LLM Reasoning
by: Wang, Xiangwei, et al.
Published: (2026)

LongEmbed: Extending Embedding Models for Long Context Retrieval
by: Zhu, Dawei, et al.
Published: (2024)

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
by: Xiong, Weimin, et al.
Published: (2026)

Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning
by: Zhang, Ziyi, et al.
Published: (2025)

Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model
by: Ling Team, et al.
Published: (2025)

STeCa: Step-level Trajectory Calibration for LLM Agent Learning
by: Wang, Hanlin, et al.
Published: (2025)

AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
by: Fan, Shengda, et al.
Published: (2026)

WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning
by: Lu, Zimu, et al.
Published: (2025)

Step-Opt: Boosting Optimization Modeling in LLMs through Iterative Data Synthesis and Structured Validation
by: Wu, Yang, et al.
Published: (2025)

Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models
by: Nie, Shuo, et al.
Published: (2026)

The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism
by: Song, Yifan, et al.
Published: (2024)

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

From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning
by: Deng, Zhirui, et al.
Published: (2024)

Watch Your Steps: Observable and Modular Chains of Thought
by: Cohen, Cassandra A., et al.
Published: (2024)

Iterative Experience Refinement of Software-Developing Agents
by: Qian, Chen, et al.
Published: (2024)

R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
by: Li, Yuan, et al.
Published: (2025)