{"topic":{"slug":"reinforcement-learning","name":"Reinforcement Learning","article_count":2,"latest_published_at":"2026-10-28T00:00:00.000Z","url":"https://listedarticles.com/topics/reinforcement-learning"},"articles":[{"slug":"introducing-particle-1","title":"Introducing Particle-1","subtitle":null,"summary":"Particle launches with Particle-1, a model RL post-trained (rank-64 LoRA, GSPO, Cascade RL) on DeepSeek V4.1 Flash to solve software engineering tasks with about 45% fewer tokens. Across Terminal-Bench 2.1, ReactBench, ADE Bench and DeepSWE 1.1 it uses 28–52% fewer output tokens and costs 34–52% less per task than the base model at comparable pass rates; available now via the Particle API.","content_type":"announcement","language":"en","canonical_url":"https://particle.ai/blog/introducing-particle-1","author":{"name":"Particle team","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Particle","url":"https://particle.ai/","listing_slug":null,"listing":null},"topics":[{"name":"AI Models","slug":"ai-models","url":"https://listedarticles.com/topics/ai-models"},{"name":"Reinforcement Learning","slug":"reinforcement-learning","url":"https://listedarticles.com/topics/reinforcement-learning"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2166,"reading_minutes":9,"published_at":"2026-10-28T00:00:00.000Z","added_at":"2026-10-28T20:19:21.719Z","updated_at":"2026-10-28T20:19:21.719Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/introducing-particle-1","markdown_url":"https://listedarticles.com/articles/introducing-particle-1.md","example":false,"citation":"Particle team, Particle. \"Introducing Particle-1.\" 28 Oct 2026. https://particle.ai/blog/introducing-particle-1 (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://particle.ai/blog/introducing-particle-1"},"snippet":null,"score":null},{"slug":"towards-universal-post-training-for-robotics","title":"Towards Universal Post-Training for Robotics","subtitle":null,"summary":"Perry Dong and Chelsea Finn on why robotics RL differs from LLM RL, what EXPO-FT gets right and wrong, and what a universal post-training recipe for real-world robots still needs.","content_type":"research","language":"en","canonical_url":"https://pd-perry.github.io/posts/post-training.html","author":{"name":"Perry Dong","url":"https://pd-perry.github.io/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Perry Dong","url":"https://pd-perry.github.io/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Robotics","slug":"robotics","url":"https://listedarticles.com/topics/robotics"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Reinforcement Learning","slug":"reinforcement-learning","url":"https://listedarticles.com/topics/reinforcement-learning"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":3484,"reading_minutes":15,"published_at":"2026-09-23T17:00:00.000Z","added_at":"2026-09-23T18:31:54.278Z","updated_at":"2026-09-23T18:31:54.278Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/towards-universal-post-training-for-robotics","markdown_url":"https://listedarticles.com/articles/towards-universal-post-training-for-robotics.md","example":false,"citation":"Perry Dong, Perry Dong. \"Towards Universal Post-Training for Robotics.\" 23 Sept 2026. https://pd-perry.github.io/posts/post-training.html (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://pd-perry.github.io/posts/post-training.html"},"snippet":null,"score":null}],"total":2,"next_offset":null}