Image de couverture de livre

Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Su, Junhao, Wan, Yuanliang, Yang, Junwei, Shi, Hengyu, Han, Tianyang, Luo, Junfeng, Qiu, Yurui
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MAN++: Scaling Momentum Auxiliary Network for Supervised Local Learning in Vision Tasks
par: Su, Junhao, et autres
Publié: (2025)

LayoutCoT: Unleashing the Deep Reasoning Potential of Large Language Models for Layout Generation
par: Shi, Hengyu, et autres
Publié: (2025)

Beyond Words and Pixels: A Benchmark for Implicit World Knowledge Reasoning in Generative Models
par: Han, Tianyang, et autres
Publié: (2025)

Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards
par: Han, Tianyang, et autres
Publié: (2026)

Rethinking Local Learning: A Cheaper and Faster Recipe for LLM Post-Training
par: Shi, Hengyu, et autres
Publié: (2026)

Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank
par: Zhu, Feiyu, et autres
Publié: (2024)

VST++: Efficient and Stronger Visual Saliency Transformer
par: Liu, Nian, et autres
Publié: (2023)

Replacement Learning: Training Neural Networks with Fewer Parameters
par: Zhang, Yuming, et autres
Publié: (2026)

STRIDE: A Tool-Assisted LLM Agent Framework for Strategic and Interactive Decision-Making
par: Li, Chuanhao, et autres
Publié: (2024)

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers
par: Qi, Zhenting, et autres
Publié: (2024)

Learning to Use Tools via Cooperative and Interactive Agents
par: Shi, Zhengliang, et autres
Publié: (2024)

Reverse Thinking Makes LLMs Stronger Reasoners
par: Chen, Justin Chih-Yao, et autres
Publié: (2024)

SinkLoRA: Enhanced Efficiency and Chat Capabilities for Long-Context Large Language Models
par: Zhang, Hengyu
Publié: (2024)

PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection
par: Ren, Botao, et autres
Publié: (2024)

ReflecTool: Towards Reflection-Aware Tool-Augmented Clinical Agents
par: Liao, Yusheng, et autres
Publié: (2024)

MARS: Memory-Enhanced Agents with Reflective Self-improvement
par: Liang, Xuechen, et autres
Publié: (2025)

SAPO: Self-Adaptive Process Optimization Makes Small Reasoners Stronger
par: Chen, Kaiyuan, et autres
Publié: (2026)

Make Continual Learning Stronger via C-Flat
par: Bian, Ang, et autres
Publié: (2024)

Temporal Regularization Makes Your Video Generator Stronger
par: Chen, Harold Haodong, et autres
Publié: (2025)

Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface
par: Hua, Wenyue, et autres
Publié: (2024)

Stronger Re-identification Attacks through Reasoning and Aggregation
par: Charpentier, Lucas Georges Gabriel, et autres
Publié: (2025)

LLM Agents Making Agent Tools
par: Wölflein, Georg, et autres
Publié: (2025)

Mistake Notebook Learning: Batch-Clustered Failures for Training-Free Agent Adaptation
par: Su, Xuanbo, et autres
Publié: (2025)

CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning
par: Wu, Mengsong, et autres
Publié: (2025)

ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering
par: Liu, Marianne Menglin, et autres
Publié: (2025)

SGDM: Static-Guided Dynamic Module Make Stronger Visual Models
par: Xing, Wenjie, et autres
Publié: (2024)

From Failure to Mastery: Generating Hard Samples for Tool-use Agents
par: Hao, Bingguang, et autres
Publié: (2026)

Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering
par: Liu, Runxuan, et autres
Publié: (2025)

TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation
par: Wang, Yaoxiang, et autres
Publié: (2024)

DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs
par: Lin, Haokun, et autres
Publié: (2024)

Stronger Models are NOT Stronger Teachers for Instruction Tuning
par: Xu, Zhangchen, et autres
Publié: (2024)

Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT
par: Zhuo, Le, et autres
Publié: (2024)

Reducing Tool Hallucination via Reliability Alignment
par: Xu, Hongshen, et autres
Publié: (2024)

XAgen: An Explainability Tool for Identifying and Correcting Failures in Multi-Agent Workflows
par: Wang, Xinru, et autres
Publié: (2025)

Towards Enhanced Immersion and Agency for LLM-based Interactive Drama
par: Wu, Hongqiu, et autres
Publié: (2025)

DermAgent: A Self-Reflective Agentic System for Dermatological Image Analysis with Multi-Tool Reasoning and Traceable Decision-Making
par: Liu, Yize, et autres
Publié: (2026)

Part-Attention Based Model Make Occluded Person Re-Identification Stronger
par: Chen, Zhihao, et autres
Publié: (2024)

Completing A Systematic Review in Hours instead of Months with Interactive AI Agents
par: Qiu, Rui, et autres
Publié: (2025)

ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling
par: Luo, Yawen, et autres
Publié: (2026)

GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation
par: He, Jie, et autres
Publié: (2025)