{"id":"arxiv:2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","date":"2025-03-18","section":"Post-training","quality":-0.315765,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/","source_url":"https://arxiv.org/abs/2503.14476","text_available":true,"authors":["Qiying Yu","Zheng Zhang","Ruofei Zhu","Yufeng Yuan"],"outgoing":[{"source":"arxiv:2503.14476","target":"arxiv:2210.10760","evidence":"title","id":"arxiv:2210.10760","title":"Scaling Laws for Reward Model Overoptimization","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/fd55acb4c34a2366d8f9c1fc0672a20be0ac4da8643118d0cbf627e891346d2d/"},{"source":"arxiv:2503.14476","target":"arxiv:2402.03300","evidence":"id","id":"arxiv:2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/636fb871904bc06f742cfdea069796f9e9665f95bd58dc63260eaff5154ef985/"}],"incoming":[{"source":"arxiv:2504.13837","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b90f70269aeb02311d74ffaadf47e139683424a47118dc18619000ba72174d17/"},{"source":"arxiv:2504.16084","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2504.16084","title":"TTRL: Test-Time Reinforcement Learning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ad54dd58d24afdfefc8aa5087d07c4aab2143e90ef06f6f7db8d3f3333452c48/"},{"source":"arxiv:2504.20571","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2504.20571","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b2b21c3df49619588c371411dba9467a41f81b3fd4da5441898b5145bb0de120/"},{"source":"arxiv:2505.10978","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2505.10978","title":"Group-in-Group Policy Optimization for LLM Agent Training","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/2fa466eef15ebc0489217004e5ebb80efd37db9675a603331ccc3b7da055d147/"},{"source":"arxiv:2505.21444","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2505.21444","title":"Can Large Reasoning Models Self-Train?","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/206224ca50098e0bdc230140722feec107cfc90c1cef2ed8d3ed52355ef56bca/"},{"source":"arxiv:2505.21493","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2505.21493","title":"Reinforcing General Reasoning without Verifiers","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/06d2ae06e1a3bcda5db4695ecca7ec78df67002bddc755936e262799f3e15d15/"},{"source":"arxiv:2506.01939","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e0f4a55bca612bce5895b6b98f89b0efc14cbd8cf45946a7743347cf6daee1a1/"},{"source":"arxiv:2506.03106","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2506.03106","title":"Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b16b5772846ee30548a2d2c9cce1833ca3af6beb01c4a58f2dd5a69d809d55d4/"},{"source":"arxiv:2506.06632","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2506.06632","title":"Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/79fda9609f9b88bb71f71f531b63ea6b5237d1c889b7ae59e9ca07c12dbe70d1/"},{"source":"arxiv:2506.08007","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2506.08007","title":"Reinforcement Pre-Training","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a5ae77d4a2dcd6843e856083ecc6c30a72563e6896503d6efdfae117b8b007e6/"},{"source":"arxiv:2506.10947","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2506.10947","title":"Spurious Rewards: Rethinking Training Signals in RLVR","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f48e13a9656d8eff1882eb80988e07a820c4799401298947deac735c004e8592/"},{"source":"arxiv:2506.13585","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5beb2ec6c7e6362f9d957219d7a205dd1adcc53f739acc0c7fd5f1f2bded4d83/"},{"source":"arxiv:2508.07629","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2508.07629","title":"Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a232533e4e78ad28d2ffe9fafe799b66cf626b18ad523d0088d9cc12f1ba1b76/"},{"source":"arxiv:2508.11408","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2508.11408","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/48594da2e3f2cdfeb17195dd033d047235fc4b4ffb65030800f64c6faedc4fbe/"},{"source":"arxiv:2509.03646","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2509.03646","title":"Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/683657af0d699b7d854ce84d95bcd53c12e152aa738c602d0982cc0d11009f08/"},{"source":"arxiv:2509.09675","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2509.09675","title":"CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f5581044978796ff7f35cb68c27963d3abbb391d35d88173ff7801242cbb1f7a/"},{"source":"arxiv:2509.13232","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2509.13232","title":"Single-stream Policy Optimization","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d699d0e034b21f3b85c3f70ce4fb95064fbf59685ce752935e6d173dac2b71f3/"},{"source":"arxiv:2509.25123","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2509.25123","title":"From $f(x)$ and $g(x)$ to $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7fdfe7abe26ee324fe7abad3ce802148163129a7c157d77bdec859c990868e03/"},{"source":"arxiv:2510.00977","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2510.00977","title":"It Takes Two: Your GRPO Is Secretly DPO","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/575241376f2282c1929931f107a0ce60fd25f0a5388ecfea6b9abbbed2f03ca6/"},{"source":"arxiv:2510.11686","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/89b1f9c1bcd283b28d316cb6cddafdd9361be5cd510b2be2a1e761c20a0fd62e/"},{"source":"arxiv:2510.13786","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2510.13786","title":"The Art of Scaling Reinforcement Learning Compute for LLMs","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/72580bcba3d9b32b2f3e83d074f626234b26dc18126edd22a5eacef927cf87da/"},{"source":"arxiv:2511.07317","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2511.07317","title":"RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c0c18cb0ae7fe76a7239f38ce819c7ac588c1184dd27c5672f868ff4e2e26605/"},{"source":"arxiv:2512.00499","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2512.00499","title":"ESPO: Entropy Importance Sampling Policy Optimization","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/342b84df2bf40f64c57ea7839579c1f337374ad9c28b16ce7d477c42e24c67b4/"},{"source":"arxiv:2512.13961","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2512.13961","title":"Olmo 3","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8daa11a9729da9879a7e95c15d4eef3bab8579d2885a14102ed09db111221802/"},{"source":"arxiv:2601.03192","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2601.03192","title":"MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/4f5bbf3318b1fe409e0ef5dad02157180b844de366d194e82ce74bc997912eff/"},{"source":"arxiv:2601.05053","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2601.05053","title":"Reinforced Efficient Reasoning via Semantically Diverse Exploration","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/74918d32c56962f9c5b2063026f5e2243a84e20c284eb3e37c882bd4681d1a11/"},{"source":"arxiv:2601.07055","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2601.07055","title":"Dr. Zero: Self-Evolving Search Agents without Training Data","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3baa3e7fc5768b75e4ef3e64c3cc5297fa42ef19b03bc918ef5352e437e1c168/"},{"source":"arxiv:2601.18734","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2601.18734","title":"Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8a352e37fa79840a4f35f86ebc39661cfc34fbfc4391cd020a69af158c63485a/"},{"source":"arxiv:2601.20802","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2601.20802","title":"Reinforcement Learning via Self-Distillation","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/6073ec3d17b9a932a68e79ae078928f4635e40fc79cfcbc31709715d1f1e1ffa/"},{"source":"arxiv:2601.21343","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2601.21343","title":"Self-Improving Pretraining: using post-trained models to pretrain better models","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/43ce1b189d6b21d445c0ce6d4d04b4352d268beb4346da43be19982402befde8/"},{"source":"arxiv:2602.09000","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2602.09000","title":"iGRPO: Self-Feedback-Driven LLM Reasoning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1cd6a66823fe24e8e2d83e817177d3a1e8cda1d7d5b59a4397f8669bee6306ae/"},{"source":"arxiv:2603.24472","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2603.24472","title":"Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d99edb6fac2f4ad6d63e98ec0a2952187ed2ae190604fbed3507b3ed56d57315/"},{"source":"arxiv:2603.25562","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2603.25562","title":"Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a66707a05c8aa09328e4a1f322a57800a3e12262a85a9a1cf195b41dc1926b32/"},{"source":"arxiv:2604.02288","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2604.02288","title":"Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3d1160029d321f2069016f7702d4ebebee0de6cd31a8f296ee220abd6f69c99b/"},{"source":"arxiv:2604.08690","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2604.08690","title":"Skip-Connected Policy Optimization for Implicit Advantage","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b5ec1244fd1b770994920ee69c200ecc134262e6011043284200eb18eb0d6c87/"},{"source":"arxiv:2604.13016","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2604.13016","title":"Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d6d7ff1e2e7b3b9c528f19f7144098920bf573f2cb411fcac5879d5d2cac93e0/"},{"source":"arxiv:2604.20659","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2604.20659","title":"GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/42caf0f9c992f5df8bac4d0f7e45c3a5bf57879661f41febd01a047694d52628/"},{"source":"arxiv:2605.12969","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2605.12969","title":"Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/30e87f5eb9beda8e09b3945d6ba1707dec761abed83c49d129a21adaed02ce45/"},{"source":"arxiv:2605.22074","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2605.22074","title":"From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e51c03db071e17a4d5403433f1037e79c3cda795e0b20f6a490df35167411dd0/"},{"source":"arxiv:2606.06021","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2606.06021","title":"OPRD: On-Policy Representation Distillation","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a16a9d7ea78c5748acc7f651c9a96663e0200d72e51d6a52c9528e1739a27d8d/"},{"source":"arxiv:2606.18810","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2606.18810","title":"Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/9c11d77c6d08392f24aab79c8b45a3a3b0f4b743dd35e150a83ee7f6fa315248/"},{"source":"arxiv:2606.23740","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2606.23740","title":"Weight-Space Geometry of Offline Reasoning Training","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e4479f0d0930797db9347855247f1c640a12d96f63d43b83ba9635561e3ff352/"},{"source":"arxiv:2608.19197","target":"arxiv:2503.14476","evidence":"id","id":"arxiv:2608.19197","title":"SPADE: Self-Play in Adaptive Synthetic Executable Environments","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c524376d6034b5d79661d6f1a444591404f4a250bcb0790d802c05e02f8249df/"},{"source":"arxiv:2608.27448","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2608.27448","title":"TTPO: Test-Time Policy Optimization","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3473ad1e90105976912e40eabe716441e830da401749e9d85b5162e1c7bbd964/"},{"source":"arxiv:2609.30652","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2609.30652","title":"Recursive Self-Improvement via On-Policy Distillation for Reasoning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/9e52af299c264dd7185057305368429cdf42deb165dd5e3fc0f9cf6ef1d612bf/"},{"source":"arxiv:2609.37633","target":"arxiv:2503.14476","evidence":"title","id":"arxiv:2609.37633","title":"RLTL;DR: Self-improvement by Internalizing Self-generated Feedback","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c7a4c1dbb0493059883d9a01c1f89d4db3644209b909e1195c5afa4d3a320999/"},{"source":"url:cameronrwolfe.substack.com/p/grpo-tricks","target":"arxiv:2503.14476","evidence":"id","id":"url:cameronrwolfe.substack.com/p/grpo-tricks","title":"GRPO++: Tricks for Making RL Actually Work (Cameron Wolfe)","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d170bc3da5b8e6a055fd511719fcc3764635236bac638947bd0a018412245eb5/"}],"text_parts":[{"start":0,"end":15820,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-1.html"},{"start":15820,"end":31730,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html"},{"start":31730,"end":33962,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-3.html"}],"contents":[{"title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","offset":0,"level":1,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-1.html#text"},{"title":"Abstract","offset":67,"level":6,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-1.html#text"},{"title":"1 Introduction","offset":1080,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-1.html#text"},{"title":"2 Preliminary","offset":3766,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-1.html#text"},{"title":"2.1 Proximal Policy Optimization (PPO)","offset":3784,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-1.html#text"},{"title":"2.2 Group Relative Policy Optimization (GRPO)","offset":5467,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-1.html#text"},{"title":"2.3 Removing KL Divergence","offset":7426,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-1.html#text"},{"title":"2.4 Rule-based Reward Modeling","offset":7935,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-1.html#text"},{"title":"3 DAPO","offset":8713,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-1.html#text"},{"title":"3.1 Raise the Ceiling: Clip-Higher","offset":10291,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-1.html#text"},{"title":"3.2 The More the Merrier: Dynamic Sampling","offset":13799,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-1.html#text"},{"title":"3.3 Rebalancing Act: Token-Level Policy Gradient Loss","offset":16179,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"3.4 Hide and Seek: Overlong Reward Shaping","offset":18667,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"3.5 Dataset Transformation","offset":20384,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"4 Experiments","offset":21263,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"4.1 Training Details","offset":21281,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"4.2 Main Results","offset":22604,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"4.3 Training Dynamics","offset":23955,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"4.4 Case Study","offset":27240,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"5 Conclusion","offset":28183,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"Contributions","offset":28882,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"Acknowledgments","offset":29821,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"Appendix A Dataset Transformation","offset":30030,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"Original Problem","offset":31107,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"Transformed Problem","offset":31319,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"Model’s output (Markdown Text)","offset":31657,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"Transformation Thought Process","offset":31693,"level":4,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-2.html#text"},{"title":"Answer Format","offset":32274,"level":4,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-3.html#text"},{"title":"Transformed Problem","offset":32317,"level":4,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-3.html#text"},{"title":"Answer Calculation for the Transformed Problem","offset":32642,"level":4,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-3.html#text"},{"title":"Final Answer","offset":32938,"level":4,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-3.html#text"},{"title":"Appendix B Supplementary Case","offset":32964,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-3.html#text"},{"title":"Instructions for reporting errors","offset":32998,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/part-3.html#text"}],"text_code_points":33962,"source_markdown":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/source.md"}