ML Newsnew | past | best | rss | submit about
Stories from July 14, 2026 (UTC)
Go back a day, month, or year. Go forward a day.
1. Coding agents think ahead of time (arxiv.org)
96 points by andre15silva 82 days ago | hide | past | pdf | 78 comments
2. GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning (arxiv.org)
4 points by handfuloflight 82 days ago | hide | past | pdf | discuss
3. LLM-as-a-Verifier: A General-Purpose Verification Framework (arxiv.org)
3 points by gmays 82 days ago | hide | past | pdf | discuss
4. The Ramanujan Challenge for AI (arxiv.org)
2 points by root-parent 82 days ago | hide | past | pdf | discuss
5. Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning (arxiv.org)
2 points by gmays 82 days ago | hide | past | pdf | discuss
6. Auditing the Risk Claims of Distributional Reinforcement Learning (arxiv.org)
2 points by sbulaev 82 days ago | hide | past | pdf | discuss
7. ModelDNA: Verifying the lineage of open-weight LLMs from weight fingerprints (arxiv.org)
2 points by saadaamir14 82 days ago | hide | past | pdf | discuss
8. CTA-Pipelining: A Latency-Oriented Spatial Scaling Method for Multi-GPU Systems (arxiv.org)
2 points by matt_d 82 days ago | hide | past | pdf | discuss
9. Gemma 4 Technical Report (arxiv.org)
1 point by gmays 82 days ago | hide | past | pdf | discuss
10. The Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge (arxiv.org)
1 point by sbulaev 82 days ago | hide | past | pdf | discuss
About | RSS | RSS (all) | HN arXiv