{"articles":[{"slug":"deeprsi-evaluating-agents-on-long-horizon-tasks-derived-from-real-ml-research","title":"DeepRSI: evaluating agents on long-horizon tasks derived from real ML research","subtitle":null,"summary":"Hillclimb introduces DeepRSI, a benchmark of 15 open-ended machine learning problems, spanning deep learning training, GPU kernel speedups, estimator improvement and algorithm optimization, that measures how far an AI agent can improve a baseline over 48 hours. It describes the methodology with public and private verifiers, Elo rankings of frontier models, and what the results suggest for recursive self-improvement.","content_type":"research","language":"en","canonical_url":"https://www.deeprsi.com/blog/","author":{"name":"Pruthvi Rajaghatta","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Hillclimb","url":"https://www.hillclimb.com","listing_slug":"hillclimb","listing":{"slug":"hillclimb","name":"hillclimb","listing_type":"company","url":"https://listedstartups.com/companies/hillclimb"}},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1848,"reading_minutes":8,"published_at":"2026-10-12T00:00:00.000Z","added_at":"2026-10-17T05:12:27.011Z","updated_at":"2026-10-17T05:12:27.011Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/deeprsi-evaluating-agents-on-long-horizon-tasks-derived-from-real-ml-research","markdown_url":"https://listedarticles.com/articles/deeprsi-evaluating-agents-on-long-horizon-tasks-derived-from-real-ml-research.md","example":false,"citation":"Pruthvi Rajaghatta, Hillclimb. \"DeepRSI: evaluating agents on long-horizon tasks derived from real ML research.\" 12 Oct 2026. https://www.deeprsi.com/blog/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.deeprsi.com/blog/"},"snippet":null,"score":null}],"total":1,"count":1,"next_offset":null,"has_more":false,"query":{"q":null,"content_type":null,"topic":null,"publisher":"hillclimb","about":null,"author":null,"language":null,"sort":"newest","limit":20,"offset":0}}