Image de couverture de livre

Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shen, Xintian, Chen, Jiawei, Zheng, Lihao, Ma, Hao, Wei, Tao, Zhan, Kun
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Evaluating the Search Agent in a Parallel World
par: Chen, Jiawei, et autres
Publié: (2026)

CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding
par: Zheng, Lihao, et autres
Publié: (2026)

MIRG-RL: Multi-Image Reasoning and Grounding with Reinforcement Learning
par: Zheng, Lihao, et autres
Publié: (2025)

COPO: Consistency-Aware Policy Optimization
par: Han, Jinghang, et autres
Publié: (2025)

MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning
par: Chen, Jiawei, et autres
Publié: (2025)

TED: Training-Free Experience Distillation for Multimodal Reasoning
par: Yuan, Shuozhi, et autres
Publié: (2026)

Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization
par: Kong, Jiawei, et autres
Publié: (2026)

Tools as Continuous Flow for Evolving Agentic Reasoning
par: Huang, Tairan, et autres
Publié: (2026)

Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning
par: Chen, Yifei, et autres
Publié: (2025)

Diving into Self-Evolving Training for Multimodal Reasoning
par: Liu, Wei, et autres
Publié: (2024)

Transductive Visual Programming: Evolving Tool Libraries from Experience for Spatial Reasoning
par: Wu, Shengguang, et autres
Publié: (2025)

PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent
par: Wang, Prince Zizhuang, et autres
Publié: (2026)

AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse
par: Zhang, Zhang, et autres
Publié: (2026)

Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents
par: Fan, Zhiyuan, et autres
Publié: (2026)

EE-MCP: Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning
par: He, Tiantian, et autres
Publié: (2026)

Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation
par: Hao, Chao, et autres
Publié: (2026)

ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment
par: Zhao, Zhengyang, et autres
Publié: (2026)

E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning
par: Guo, Weiyang, et autres
Publié: (2026)

From Passive Reuse to Active Reasoning: Grounding Large Language Models for Neuro-Symbolic Experience Replay
par: Xiao, Yanan, et autres
Publié: (2026)

AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse
par: Yu, Zichao, et autres
Publié: (2025)

Mem$^2$Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation
par: Cheng, Zihao, et autres
Publié: (2026)

Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts
par: Ahmed, Ammar, et autres
Publié: (2025)

ReCreate: Reasoning and Creating Domain Agents Driven by Experience
par: Hao, Zhezheng, et autres
Publié: (2026)

ClueTracer: Question-to-Vision Clue Tracing for Training-Free Hallucination Suppression in Multimodal Reasoning
par: Xi, Gongli, et autres
Publié: (2026)

GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning
par: Han, Xiao, et autres
Publié: (2026)

C-World: A Computer Use Agent Environment Creator
par: Xi, Ziqiao, et autres
Publié: (2026)

HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning
par: Xu, Beibei, et autres
Publié: (2026)

To See or To Read: User Behavior Reasoning in Multimodal LLMs
par: Dong, Tianning, et autres
Publié: (2025)

FitText: Evolving Agent Tool Ecologies via Memetic Retrieval
par: Zheng, Kyle, et autres
Publié: (2026)

Real-Time Reasoning Agents in Evolving Environments
par: Wen, Yule, et autres
Publié: (2025)

Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models
par: Chen, Jie, et autres
Publié: (2024)

Evolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting
par: Ye, Kai, et autres
Publié: (2025)

MetaAgent: Toward Self-Evolving Agent via Tool Meta-Learning
par: Qian, Hongjin, et autres
Publié: (2025)

Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning
par: Tang, Jing, et autres
Publié: (2026)

ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
par: Ouyang, Siru, et autres
Publié: (2025)

EvoTool: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection
par: Yang, Shuo, et autres
Publié: (2026)

Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
par: Li, Sijia, et autres
Publié: (2025)

EGL-SCA: Structural Credit Assignment for Co-Evolving Instructions and Tools in Graph Reasoning Agents
par: Yuan, Zike, et autres
Publié: (2026)

Entropy-Guided Data-Efficient Training for Multimodal Reasoning Reward Models
par: Yang, Shidong, et autres
Publié: (2026)

Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning
par: Wu, Wenjie, et autres
Publié: (2025)