{"total":67,"papers":[{"id":"arxiv:2601.18734","title":"Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models","date":"2026-01-26","section":"Post-training","quality":0.122413,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8a352e37fa79840a4f35f86ebc39661cfc34fbfc4391cd020a69af158c63485a/","source_url":"https://arxiv.org/abs/2601.18734","text_available":true},{"id":"arxiv:2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","date":"2023-03-30","section":"Post-training","quality":0.100328,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/accef2157d87cf33be93cb3a9af246528b0a3742a9e2e700a194956fac8f5cf4/","source_url":"https://arxiv.org/abs/2303.17651","text_available":true},{"id":"arxiv:2509.13232","title":"Single-stream Policy Optimization","date":"2025-09-16","section":"Post-training","quality":-0.068041,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d699d0e034b21f3b85c3f70ce4fb95064fbf59685ce752935e6d173dac2b71f3/","source_url":"https://arxiv.org/abs/2509.13232","text_available":true},{"id":"arxiv:2604.08690","title":"Skip-Connected Policy Optimization for Implicit Advantage","date":"2026-04-09","section":"Post-training","quality":0.295907,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b5ec1244fd1b770994920ee69c200ecc134262e6011043284200eb18eb0d6c87/","source_url":"https://arxiv.org/abs/2604.08690","text_available":true},{"id":"arxiv:2511.20347","title":"Soft Adaptive Policy Optimization","date":"2025-11-25","section":"Post-training","quality":0.121839,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1e74c1ffcb5ea955bca4e6d610e9ba590965617f13bd8868f7f31e7b42fbfbfd/","source_url":"https://arxiv.org/abs/2511.20347","text_available":true},{"id":"arxiv:2601.11061","title":"Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs","date":"2026-01-16","section":"Post-training","quality":0.396869,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/96002027cf4c274573f7320398481a0cd73dbf72f18d7f37c783605f5158ea7b/","source_url":"https://arxiv.org/abs/2601.11061","text_available":true},{"id":"arxiv:2512.02807","title":"SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment","date":"2025-12-02","section":"Post-training","quality":0.238309,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ebb3b04baa11b5d0365ca4445da1c2f833108b680ea65272710ed66a57751c0e/","source_url":"https://arxiv.org/abs/2512.02807","text_available":true},{"id":"arxiv:2510.13786","title":"The Art of Scaling Reinforcement Learning Compute for LLMs","date":"2025-10-15","section":"Post-training","quality":0.419492,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/72580bcba3d9b32b2f3e83d074f626234b26dc18126edd22a5eacef927cf87da/","source_url":"https://arxiv.org/abs/2510.13786","text_available":true},{"id":"arxiv:2503.02875","title":"The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models","date":"2025-03-04","section":"Post-training","quality":-0.063911,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b9349378a2ea40a7998ba364a4587c40dff3cc9b22750e14b3b21e296a4ecb12/","source_url":"https://arxiv.org/abs/2503.02875","text_available":true},{"id":"arxiv:2607.05609","title":"To Retain or to Adapt? Generalizing Continual Learning","date":"2026-07-06","section":"Post-training","quality":0.077814,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/de2d99f43688431acd6fa456a50322ed0f00aa30d884a6767719f8a73b3b7c45/","source_url":"https://arxiv.org/abs/2607.05609","text_available":true},{"id":"arxiv:2601.14525","title":"Towards Execution-Grounded Automated AI Research","date":"2026-01-20","section":"Post-training","quality":0.042877,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/895006e818735c9a565dbe99ae31404366eefd6bdc2278612271c65a8493e4a5/","source_url":"https://arxiv.org/abs/2601.14525","text_available":true},{"id":"arxiv:2608.27448","title":"TTPO: Test-Time Policy Optimization","date":"2026-08-27","section":"Post-training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3473ad1e90105976912e40eabe716441e830da401749e9d85b5162e1c7bbd964/","source_url":"https://arxiv.org/abs/2608.27448","text_available":true},{"id":"arxiv:2504.16084","title":"TTRL: Test-Time Reinforcement Learning","date":"2025-04-22","section":"Post-training","quality":0.322393,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ad54dd58d24afdfefc8aa5087d07c4aab2143e90ef06f6f7db8d3f3333452c48/","source_url":"https://arxiv.org/abs/2504.16084","text_available":true},{"id":"arxiv:2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","date":"2025-03-26","section":"Post-training","quality":0.335057,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b49a056f3ce8e269dd65e3b11605927f3c4d0ef074bc68e0b1d7f84e6c9c6c6a/","source_url":"https://arxiv.org/abs/2503.20783","text_available":true},{"id":"arxiv:2604.02288","title":"Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing","date":"2026-04-02","section":"Post-training","quality":0.005794,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3d1160029d321f2069016f7702d4ebebee0de6cd31a8f296ee220abd6f69c99b/","source_url":"https://arxiv.org/abs/2604.02288","text_available":true},{"id":"arxiv:2506.10139","title":"Unsupervised Elicitation of Language Models","date":"2025-06-11","section":"Post-training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f27ae3b426a87310071610dedea4c144b50b1be183434e32486b31562f9a3da9/","source_url":"https://arxiv.org/abs/2506.10139","text_available":true},{"id":"arxiv:2606.23740","title":"Weight-Space Geometry of Offline Reasoning Training","date":"2026-06-26","section":"Post-training","quality":-0.244397,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e4479f0d0930797db9347855247f1c640a12d96f63d43b83ba9635561e3ff352/","source_url":"https://arxiv.org/abs/2606.23740","text_available":true},{"id":"arxiv:2607.07847","title":"When Does Continual Learning Require Learning","date":"2026-07-08","section":"Post-training","quality":0.0211,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/86e88c6cf21a66879eab5c156913fc85d14eb69c394c78c33c0e81d144e528eb/","source_url":"https://arxiv.org/abs/2607.07847","text_available":true},{"id":"arxiv:2603.24472","title":"Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?","date":"2026-03-25","section":"Post-training","quality":-0.15648,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d99edb6fac2f4ad6d63e98ec0a2952187ed2ae190604fbed3507b3ed56d57315/","source_url":"https://arxiv.org/abs/2603.24472","text_available":true}],"next":null}