Image de couverture de livre

Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gao, Xingjie, Huang, Pengcheng, Liu, Zhenghao, Yan, Yukun, Wang, Shuo, Chen, Zulong, Qian, Chen, Yu, Ge, Gu, Yu
Format:	Preprint
Publié:	2026
Sujets:	Software Engineering Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis
par: Yang, Weiqing, et autres
Publié: (2024)

An Empirical Study of Interaction Bugs in ROS-based Software
par: Chen, Zhixiang, et autres
Publié: (2025)

INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair
par: Wang, Hanbin, et autres
Publié: (2023)

Sifting through the Chaff: On Utilizing Execution Feedback for Ranking the Generated Code Candidates
par: Sun, Zhihong, et autres
Publié: (2024)

CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification
par: Tian, Yuchen, et autres
Publié: (2024)

Simulating Complex Multi-Turn Tool Calling Interactions in Stateless Execution Environments
par: Crouse, Maxwell, et autres
Publié: (2026)

Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation
par: Wang, Chong, et autres
Publié: (2024)

Integrating Symbolic Execution with LLMs for Automated Generation of Program Specifications
par: Yang, Fanpeng, et autres
Publié: (2025)

Can Large Language Models Solve Path Constraints in Symbolic Execution?
par: Wang, Wenhan, et autres
Publié: (2025)

Hyperion: Unveiling DApp Inconsistencies using LLM and Dataflow-Guided Symbolic Execution
par: Yang, Shuo, et autres
Publié: (2024)

Logging Like Humans for LLMs: Rethinking Logging via Execution and Runtime Feedback
par: Wang, Xin, et autres
Publié: (2026)

SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
par: Xia, Hongfei, et autres
Publié: (2025)

SelfPiCo: Self-Guided Partial Code Execution with LLMs
par: Xue, Zhipeng, et autres
Publié: (2024)

Compiling Code LLMs into Lightweight Executables
par: Shi, Jieke, et autres
Publié: (2026)

CodeScore: Evaluating Code Generation by Learning Code Execution
par: Dong, Yihong, et autres
Publié: (2023)

NumScout: Unveiling Numerical Defects in Smart Contracts using LLM-Pruning Symbolic Execution
par: Chen, Jiachi, et autres
Publié: (2025)

Mokav: Execution-driven Differential Testing with LLMs
par: Etemadi, Khashayar, et autres
Publié: (2024)

An Executable Benchmarking Suite for Tool-Using Agents
par: Zhong, Zhiqing, et autres
Publié: (2026)

Teaching LLMs Program Semantics via Symbolic Execution Traces
par: Bayer, Jonas, et autres
Publié: (2026)

VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security Specifications
par: Zhu, Hao, et autres
Publié: (2025)

A Hybrid Execution Environment for Computer-Interpretable Guidelines in PROforma
par: Kogan, Alexandra, et autres
Publié: (2024)

Python Symbolic Execution with LLM-powered Code Generation
par: Wang, Wenhan, et autres
Publié: (2024)

Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages
par: Wu, Fan, et autres
Publié: (2026)

A Tool for In-depth Analysis of Code Execution Reasoning of Large Language Models
par: Liu, Changshu, et autres
Publié: (2025)

Learning Adaptive Parallel Execution for Efficient Code Localization
par: Xu, Ke, et autres
Publié: (2026)

The A-R Behavioral Space: Execution-Level Profiling of Tool-Using Language Model Agents in Organizational Deployment
par: Yu, Shasha, et autres
Publié: (2026)

Seismology modeling agent: A smart assistant for geophysical researchers
par: Ren, Yukun, et autres
Publié: (2025)

ResearchEnvBench: Benchmarking Agents on Environment Synthesis for Research Code Execution
par: Wang, Yubang, et autres
Publié: (2026)

Disproving Program Equivalence with LLMs
par: Allamanis, Miltiadis, et autres
Publié: (2025)

Leveraging LLMs for Dynamic IoT Systems Generation through Mixed-Initiative Interaction
par: Adnan, Bassam, et autres
Publié: (2025)

SynthCoder: A Synthetical Strategy to Tune LLMs for Code Completion
par: Yu, Dongjun, et autres
Publié: (2025)

ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation
par: He, Minghua, et autres
Publié: (2025)

Can LLMs Recover Program Semantics? A Systematic Evaluation with Symbolic Execution
par: Feng, Rong, et autres
Publié: (2025)

Development of a Evaluation Tool for Age-Appropriate Software in Aging Environments: A Delphi Study
par: Bai, Zhenggang, et autres
Publié: (2024)

Identifying Process Improvement Opportunities through Process Execution Benchmarking
par: Abb, Luka, et autres
Publié: (2025)

Execution-free Program Repair
par: Huang, Li, et autres
Publié: (2024)

NExT: Teaching Large Language Models to Reason about Code Execution
par: Ni, Ansong, et autres
Publié: (2024)

Analyzing C/C++ Library Migrations at the Package-level: Prevalence, Domains, Targets and Rationals across Seven Package Management Tools
par: Gu, Haiqiao, et autres
Publié: (2025)

CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation
par: Chen, Zaoyu, et autres
Publié: (2026)

DOne: Decoupling Structure and Rendering for High-Fidelity Design-to-Code Generation
par: Huang, Xinhao, et autres
Publié: (2026)