Copertina

Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Zeping, Wang, Hongru, Zhao, Yiwen, Chen, Guanhua, Li, Yixia, Chen, Keyang, Cao, Yixin, Ye, Guangnan, Chai, Hongfeng, Yin, Zhenfei
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Behavioral Consistency Validation for LLM Agents: An Analysis of Trading-Style Switching through Stock-Market Simulation
di: Li, Zeping, et al.
Pubblicazione: (2026)

GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generation
di: Wang, Yifan, et al.
Pubblicazione: (2026)

From Word to World: Can Large Language Models be Implicit Text-based World Models?
di: Li, Yixia, et al.
Pubblicazione: (2025)

Online-Optimized RAG for Tool Use and Function Calling
di: Pan, Yu, et al.
Pubblicazione: (2025)

SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?
di: Chen, Shiqi, et al.
Pubblicazione: (2026)

MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
di: Huang, Yue, et al.
Pubblicazione: (2023)

Environment-in-the-Loop: Rethinking Code Migration with LLM-based Agents
di: Li, Xiang, et al.
Pubblicazione: (2026)

SilverSight: A Multi-Task Chinese Financial Large Language Model Based on Adaptive Semantic Space Learning
di: Zhou, Yuhang, et al.
Pubblicazione: (2024)

Benchmarking and Studying the LLM-based Agent System in End-to-End Software Development
di: Zeng, Zhengran, et al.
Pubblicazione: (2025)

HerAgent: Rethinking the Automated Environment Deployment via Hierarchical Test Pyramid
di: Li, Xiang, et al.
Pubblicazione: (2026)

Towards Verifiably Safe Tool Use for LLM Agents
di: Doshi, Aarya, et al.
Pubblicazione: (2026)

The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration
di: Xu, Haoyuan, et al.
Pubblicazione: (2026)

TransXion: A High-Fidelity Graph Benchmark for Realistic Anti-Money Laundering
di: Chen, Keyang, et al.
Pubblicazione: (2026)

CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent System
di: Hu, Li, et al.
Pubblicazione: (2025)

ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering
di: Liu, Marianne Menglin, et al.
Pubblicazione: (2025)

Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities
di: Chen, Simin, et al.
Pubblicazione: (2025)

SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
di: Xia, Hongfei, et al.
Pubblicazione: (2025)

An End-to-End Approach for Fixing Concurrency Bugs via SHB-Based Context Extractor
di: Li, Zhuang, et al.
Pubblicazione: (2026)

A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning
di: Li, Xinzhe
Pubblicazione: (2024)

DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
di: Chen, Aili, et al.
Pubblicazione: (2026)

CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
di: Zhang, Kechi, et al.
Pubblicazione: (2024)

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox
di: Li, Yuanyang, et al.
Pubblicazione: (2026)

Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents
di: Chen, Zhi, et al.
Pubblicazione: (2026)

Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation
di: Wang, Chong, et al.
Pubblicazione: (2024)

ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents
di: Li, Dawei, et al.
Pubblicazione: (2026)

SMARTCAL: An Approach to Self-Aware Tool-Use Evaluation and Calibration
di: Shen, Yuanhao, et al.
Pubblicazione: (2024)

AI Tool Use and Adoption in Software Development by Individuals and Organizations: A Grounded Theory Study
di: Li, Ze Shi, et al.
Pubblicazione: (2024)

An Executable Benchmarking Suite for Tool-Using Agents
di: Zhong, Zhiqing, et al.
Pubblicazione: (2026)

RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement
di: LeVine, Will, et al.
Pubblicazione: (2026)

Collaboration Tools and their Role in Agile Software Projects
di: Hussein, Raman Mohammed, et al.
Pubblicazione: (2025)

Same Signal, Different Semantics: A Cross-Framework Behavioral Analysis of Software Engineering Agents
di: Ma, Wei, et al.
Pubblicazione: (2026)

SynthTools: A Framework for Scaling Synthetic Tools for Agent Development
di: Castellani, Tommaso, et al.
Pubblicazione: (2025)

Identifying Root Cause of bugs by Capturing Changed Code Lines with Relational Graph Neural Networks
di: Zhang, Jiaqi, et al.
Pubblicazione: (2025)

AgentFM: Role-Aware Failure Management for Distributed Databases with LLM-Driven Multi-Agents
di: Zhang, Lingzhe, et al.
Pubblicazione: (2025)

ToolFuzz -- Automated Agent Tool Testing
di: Milev, Ivan, et al.
Pubblicazione: (2025)

JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents
di: Ghoshal, Sandip, et al.
Pubblicazione: (2026)

TypeScript Repository Indexing for Code Agent Retrieval
di: Pu, Junsong, et al.
Pubblicazione: (2026)

A Tool for Generating Exceptional Behavior Tests With Large Language Models
di: Zhong, Linghan, et al.
Pubblicazione: (2025)

ROOT: Requirements Organization and Optimization Tool
di: Dearstyne, Katherine R., et al.
Pubblicazione: (2024)

ToolScan: A Benchmark for Characterizing Errors in Tool-Use LLMs
di: Kokane, Shirley, et al.
Pubblicazione: (2024)