One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents Paper • 2512.20957 • Published Dec 24, 2025 • 2
CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents Paper • 2607.25431 • Published 12 days ago • 112
CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents Paper • 2607.25431 • Published 12 days ago • 112
CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents Paper • 2607.25431 • Published 12 days ago • 112
view article Article Welcome Gemma 4: Frontier multimodal intelligence on device +5 merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift • Apr 2 • 919
EvoClaw: Evaluating AI Agents on Continuous Software Evolution Paper • 2603.13428 • Published Mar 13 • 22
EvoClaw: Evaluating AI Agents on Continuous Software Evolution Paper • 2603.13428 • Published Mar 13 • 22
Running Agents 8 AMA-Bench Leaderboard 🧠8 Visualize model performance across capabilities and domains
Running Agents 8 AMA-Bench Leaderboard 🧠8 Visualize model performance across capabilities and domains
Efficient Long-context Language Model Training by Core Attention Disaggregation Paper • 2510.18121 • Published Oct 20, 2025 • 124