 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from February 16, 2026 (UTC)
|
| 1. | SkillsBench: Benchmarking how well agent skills work across diverse tasks (arxiv.org) |
| 364 points by mustaphah 230 days ago | hide | past | pdf | 171 comments | |
| 2. | Evaluating AGENTS.md: are they helpful for coding agents? (arxiv.org) |
| 232 points by mustaphah 230 days ago | hide | past | pdf | 161 comments | |
| 3. | Virtual Width Networks (VWN) (arxiv.org) |
| 9 points by tesserato 230 days ago | hide | past | pdf | discuss | |
| 4. | Soft Contamination Means Benchmarks Test Shallow Generalization (arxiv.org) |
| 2 points by cjbarber 230 days ago | hide | past | pdf | 1 comment | |
| 5. | CodeLogician: Neuro-symbolic reasoning for precise software analysis (arxiv.org) |
| 2 points by NTCTech 230 days ago | hide | past | pdf | 1 comment | |
| 6. | Delegated Agent Authorization Constrained to Semantic Task-to-Scope Matching (arxiv.org) |
| 1 point by mooreds 230 days ago | hide | past | pdf | discuss | |