{"total":415,"papers":[{"id":"acl:2022.acl-long.360","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","date":"2021-10-16","section":"Retrieval, embeddings, benchmarks","quality":-0.070728,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7ea72ee4d97ca9c2839284c71ef41df5bb2db7ca0ab28e219c275e13139eaace/","source_url":"https://aclanthology.org/2022.acl-long.360/","text_available":true},{"id":"arxiv:1511.05952","title":"Prioritized Experience Replay","date":"2015-11-18","section":"Reinforcement learning","quality":-0.008072,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c88bf0c11c1817dcc457c001dfef5cd120a0946c8a009a0fe40648dae03eb7d4/","source_url":"https://arxiv.org/abs/1511.05952","text_available":true},{"id":"url:github.com/alexisfox7/rgb-agent","title":"PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning","date":"2026-07-22","section":"Harness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d9edca36213ad054416ec660f6590afe60c60edd809bcb76c366c99b442cc929/","source_url":"https://github.com/alexisfox7/RGB-Agent","text_available":false},{"id":"arxiv:2301.05217","title":"Progress measures for grokking via mechanistic interpretability","date":"2023-01-12","section":"Reasoning and the \"physics\" of language models","quality":0.649164,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f71e3b65a8b3f35beb171d17f6c65878e0914227a0042ccba59b88952554baef/","source_url":"https://arxiv.org/abs/2301.05217","text_available":true},{"id":"arxiv:2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","date":"2023-09-28","section":"Retrieval, embeddings, benchmarks","quality":-0.189598,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/daac3bcfcd7f39084d995905e9ef96ae01c5aab7bfe8e565bd7622b4e44088f7/","source_url":"https://arxiv.org/abs/2309.16797","text_available":true},{"id":"arxiv:2507.01098","title":"Proof of a perfect platonic representation hypothesis","date":"2025-07-01","section":"Representation alignment","quality":-0.084344,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/39afe7519b574380221abb205b8d481666b312a8b366e8145fe64c41caad5c32/","source_url":"https://arxiv.org/abs/2507.01098","text_available":true},{"id":"arxiv:2512.18160","title":"Propose, Solve, Verify: Self-Play Through Formal Verification","date":"2025-12-20","section":"Agents, open-endedness, AGI","quality":0.112256,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/6b68bf20c3b0180fbf31bfbfb5f4e5f7800fc134d2c393106efb3320b67a64cd/","source_url":"https://arxiv.org/abs/2512.18160","text_available":true},{"id":"arxiv:2608.27370","title":"Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090","date":"2026-08-27","section":"Data, training, optimization","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e7c6bd97e97892c4e1efe65bec9c8dd703a7e817d9544e8b27822583311ab5ab/","source_url":"https://arxiv.org/abs/2608.27370","text_available":true},{"id":"arxiv:2608.17163","title":"Q-Learning With World Models","date":"2026-08-17","section":"Reinforcement learning","quality":0.08444,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/15ca8843297a713249e241e591505a44859dac258c54e299d79c62c81bd893c2/","source_url":"https://arxiv.org/abs/2608.17163","text_available":true},{"id":"arxiv:2402.16822","title":"Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts","date":"2024-02-26","section":"Retrieval, embeddings, benchmarks","quality":0.383425,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d4803e891a4b9c929eca007e3c3f003c330d2fc741109975c6ddd7d2c32828fc/","source_url":"https://arxiv.org/abs/2402.16822","text_available":true},{"id":"arxiv:1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","date":"2017-10-06","section":"Reinforcement learning","quality":-0.054363,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/4183a5aecdb6558733bd0b2028e6197904c8b46173181bf6c8270fb6cbcfc973/","source_url":"https://arxiv.org/abs/1710.02298","text_available":true},{"id":"url:anthropic.com/research/reasoning-models-dont-say-think","title":"Reasoning Models Don't Always Say What They Think","date":"2025-05-08","section":"AI safety and consciousness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/4ca0654119289c784e751677f3ce63742c77f58afe54849ad74eafb2d1bccb8a/","source_url":"https://www.anthropic.com/research/reasoning-models-dont-say-think","text_available":false},{"id":"arxiv:2609.33540","title":"Reasoning on the Simplex: Geometric Fixed-Point Models","date":"2026-09-27","section":"Reasoning and the \"physics\" of language models","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d8882e1cc48049a4b6b9a911701665da57fcc16f9e52f2b403b1a5b334653d9c/","source_url":"https://arxiv.org/abs/2609.33540","text_available":true},{"id":"arxiv:2510.14901","title":"Reasoning with Sampling: Your Base Model is Smarter Than You Think","date":"2025-10-16","section":"Post-training","quality":0.212422,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/46373e6f386387299bbade0a302219a611c3497c5e5b5970e3502f7a5f189687/","source_url":"https://arxiv.org/abs/2510.14901","text_available":true},{"id":"arxiv:2608.17981","title":"Recirculation","date":"2026-08-18","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/fd91ffc957070136795d3728f662c997738234065b624eb720acd8547d2edaf6/","source_url":"https://arxiv.org/abs/2608.17981","text_available":true},{"id":"arxiv:2512.24601","title":"Recursive Language Models","date":"2025-12-31","section":"LLMs: architectures, context, training","quality":0.153868,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ac41983c934a3432ce7b6531e367b9e639bddbed93d4c6513781e76407d9a8bd/","source_url":"https://arxiv.org/abs/2512.24601","text_available":true},{"id":"arxiv:2609.30652","title":"Recursive Self-Improvement via On-Policy Distillation for Reasoning","date":"2026-09-25","section":"Post-training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/9e52af299c264dd7185057305368429cdf42deb165dd5e3fc0f9cf6ef1d612bf/","source_url":"https://arxiv.org/abs/2609.30652","text_available":true},{"id":"arxiv:2601.05053","title":"Reinforced Efficient Reasoning via Semantically Diverse Exploration","date":"2026-01-08","section":"Post-training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/74918d32c56962f9c5b2063026f5e2243a84e20c284eb3e37c882bd4681d1a11/","source_url":"https://arxiv.org/abs/2601.05053","text_available":true},{"id":"arxiv:2504.20571","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","date":"2025-04-29","section":"Reasoning and the \"physics\" of language models","quality":0.214668,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b2b21c3df49619588c371411dba9467a41f81b3fd4da5441898b5145bb0de120/","source_url":"https://arxiv.org/abs/2504.20571","text_available":true},{"id":"url:rlhfbook.com","title":"Reinforcement Learning from Human Feedback","date":"2024-05-24","section":"Books","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/20e354559fad09ad4d6338d104c9c3f822a48e7fbf86cd8afa1ddf951b223658/","source_url":"https://rlhfbook.com/","text_available":false},{"id":"arxiv:2201.09746","title":"Reinforcement Learning Textbook","date":"2022-01-19","section":"Books","quality":-0.586946,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/858e0104d53b9ae09818c743578349bb5385c3aed320640a292c13f01ea5b6d8/","source_url":"https://arxiv.org/abs/2201.09746","text_available":true},{"id":"arxiv:2601.20802","title":"Reinforcement Learning via Self-Distillation","date":"2026-01-28","section":"Post-training","quality":0.277712,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/6073ec3d17b9a932a68e79ae078928f4635e40fc79cfcbc31709715d1f1e1ffa/","source_url":"https://arxiv.org/abs/2601.20802","text_available":true},{"id":"arxiv:2506.08007","title":"Reinforcement Pre-Training","date":"2025-06-09","section":"Data, training, optimization","quality":-0.408418,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a5ae77d4a2dcd6843e856083ecc6c30a72563e6896503d6efdfae117b8b007e6/","source_url":"https://arxiv.org/abs/2506.08007","text_available":true},{"id":"arxiv:2505.21493","title":"Reinforcing General Reasoning without Verifiers","date":"2025-05-27","section":"Reasoning and the \"physics\" of language models","quality":0.501779,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/06d2ae06e1a3bcda5db4695ecca7ec78df67002bddc755936e262799f3e15d15/","source_url":"https://arxiv.org/abs/2505.21493","text_available":true}],"next":"https://vinnik-dmitry07.github.io/favorite-papers/agents/catalog-0-13.html"}