2502.18449

arxiv.org · 13,342 words · saved by 1 readers

N/A

# link_1ko7lky355n.pdf ## Metadata - PDFFormatVersion=1.7 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - Author=Yuxiang Wei; Olivier Duchenne; Jade Copet; Quentin Carbonneaux; Lingming Zhang; Daniel Fried; Gabriel Synnaeve; Rishabh Singh; Sida I. Wang - Creator=arXiv GenPDF (tex2pdf:4177c2c) - Custom.DOI=https://doi.org/10.48550/arXiv.2502.18449 - Custom.License=http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.141592653-2.6-1.40.28 (TeX Live 2025) kpathsea versio

saved by

Daniel R

related reading

Toward Training Superintelligent Software Agents through Self-Play SWE-RLarxiv.org
Self-Adapting Language Modelsarxiv.org
[2512.18552] Toward Training Superintelligent Software Agents through Self-Play SWE-RLarxiv.org
[2604.22082] Removing Sandbagging in LLMs by Training with Weak Supervisionarxiv.org
[2502.17424] Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMsarxiv.org
[2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
[2607.00053] SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasksarxiv.org
[2507.19457] GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learningarxiv.org
[2604.16812] Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org
Large Language Diffusion Modelsarxiv.org
[2410.06992] SWE-Bench+: Enhanced Coding Benchmark for LLMsar5iv.labs.arxiv.org
2401.10020.pdfarxiv.org