Imagen de Portada

PostTrainBench: Can LLM Agents Automate LLM Post-Training?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Rank, Ben, Bhatnagar, Hardik, Prabhu, Ameya, Eisenberg, Shira, Nguyen, Karina, Bethge, Matthias, Andriushchenko, Maksym
Formato:	Preprint
Publicado:	2026
Materias:	Software Engineering Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuning
por: Zhang, Lingzhe, et al.
Publicado: (2026)

Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation
por: Sinha, Shiven, et al.
Publicado: (2025)

From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection
por: Li, Youpeng, et al.
Publicado: (2026)

Mapping Post-Training Forgetting in Language Models at Scale
por: Harmon, Jackson, et al.
Publicado: (2025)

Post-hoc LLM-Supported Debugging of Distributed Processes
por: Schiese, Dennis, et al.
Publicado: (2025)

Verification Limits Code LLM Training
por: Gureja, Srishti, et al.
Publicado: (2025)

BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks
por: Tu, Xinming, et al.
Publicado: (2026)

Evolving Excellence: Automated Optimization of LLM-based Agents
por: Brookes, Paul, et al.
Publicado: (2025)

LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering
por: Qiu, Jielin, et al.
Publicado: (2025)

PyBench: Evaluating LLM Agent on various real-world coding tasks
por: Zhang, Yaolun, et al.
Publicado: (2024)

An Empirical Study on LLM-based Agents for Automated Bug Fixing
por: Meng, Xiangxin, et al.
Publicado: (2024)

DataGovBench: Benchmarking LLM Agents for Real-World Data Governance Workflows
por: Liu, Zhou, et al.
Publicado: (2025)

MemoCoder: Automated Function Synthesis using LLM-Supported Agents
por: Jia, Yiping, et al.
Publicado: (2025)

ContractBench: Can LLM Agents Preserve Observation Contracts?
por: Wang, Jicheng, et al.
Publicado: (2026)

ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents
por: He, Jiawei, et al.
Publicado: (2026)

Good things come in three: Generating SO Post Titles with Pre-Trained Models, Self Improvement and Post Ranking
por: Le, Duc Anh, et al.
Publicado: (2024)

iPanda: An LLM-based Agent for Automated Conformance Testing of Communication Protocols
por: Sun, Xikai, et al.
Publicado: (2025)

Cracks in The Stack: Hidden Vulnerabilities and Licensing Risks in LLM Pre-Training Datasets
por: Jahanshahi, Mahmoud, et al.
Publicado: (2025)

Z-Space: A Multi-Agent Tool Orchestration Framework for Enterprise-Grade LLM Automation
por: He, Qingsong, et al.
Publicado: (2025)

Guarded Repair for Harm-Aware Post-hoc Replacement of LLM Mathematical Reasoning
por: Xia, Haizhou
Publicado: (2026)

CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories
por: Xiao, Yijia, et al.
Publicado: (2025)

Automating Android Build Repair: Bridging the Reasoning-Execution Gap in LLM Agents with Domain-Specific Tools
por: Son, Ha Min, et al.
Publicado: (2025)

PerfBench: Can Agents Resolve Real-World Performance Bugs?
por: Garg, Spandan, et al.
Publicado: (2025)

Can LLM Generate Regression Tests for Software Commits?
por: Liu, Jing, et al.
Publicado: (2025)

Can an LLM Detect Instances of Microservice Infrastructure Patterns?
por: Duarte, Carlos Eduardo, et al.
Publicado: (2026)

BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software
por: Zhang, Zehua, et al.
Publicado: (2025)

AgenticTCAD: A LLM-based Multi-Agent Framework for Automated TCAD Code Generation and Device Optimization
por: Fan, Guangxi, et al.
Publicado: (2025)

AutoDroid: LLM-powered Task Automation in Android
por: Wen, Hao, et al.
Publicado: (2023)

LLM Agents for Automated Dependency Upgrades
por: Tawosi, Vali, et al.
Publicado: (2025)

Automated Program Repair of Uncompilable Student Code
por: Pitts, Griffin, et al.
Publicado: (2025)

Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systems
por: Martinez, Matias, et al.
Publicado: (2025)

RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
por: Bouzenia, Islem, et al.
Publicado: (2024)

EvolveTool-Bench: Evaluating the Quality of LLM-Generated Tool Libraries as Software Artifacts
por: Kaliyev, Alibek T., et al.
Publicado: (2026)

LLM-Based Automated Diagnosis Of Integration Test Failures At Google
por: Ziftci, Celal, et al.
Publicado: (2026)

Automated Validation of LLM-based Evaluators for Software Engineering Artifacts
por: Fandina, Ora Nova, et al.
Publicado: (2025)

LLM-Driven Kernel Evolution: Automating Driver Updates in Linux
por: Kharlamova, Arina, et al.
Publicado: (2025)

SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair
por: Gajjar, Jugal, et al.
Publicado: (2025)

Reducing Cost of LLM Agents with Trajectory Reduction
por: Xiao, Yuan-An, et al.
Publicado: (2025)

LLM Collaboration With Multi-Agent Reinforcement Learning
por: Liu, Shuo, et al.
Publicado: (2025)

SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training
por: Song, Huatong, et al.
Publicado: (2026)