{"total":415,"papers":[{"id":"arxiv:2601.21557","title":"Meta Context Engineering via Agentic Skill Evolution","date":"2026-01-29","section":"Agents, open-endedness, AGI","quality":0.035459,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/bedaeecadf58846f4728c50c03396fc96ba18429ecf14052b4c5e177394a246e/","source_url":"https://arxiv.org/abs/2601.21557","text_available":true},{"id":"arxiv:2603.28052","title":"Meta-Harness: End-to-End Optimization of Model Harnesses","date":"2026-03-30","section":"Harness","quality":0.315536,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8bb0b87384dfdd42c419cf26cc7e52f1f0d89f63afa5d5968e246b73a44c99cb/","source_url":"https://arxiv.org/abs/2603.28052","text_available":true},{"id":"arxiv:2312.00276","title":"Metalearning Continual Learning Algorithms","date":"2023-12-01","section":"Reinforcement learning","quality":0.12499,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5d7361f404c0455d9f759fc6a8dd7bd1da75146e72717b7a2fbcdb8bac80412a/","source_url":"https://arxiv.org/abs/2312.00276","text_available":true},{"id":"arxiv:2402.02342","title":"MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters","date":"2024-02-04","section":"Data, training, optimization","quality":-0.208417,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/6801d4fe20b85924aed2dec1855a35232b2ec1d98e15ec3bc27a0fbe5dfd1af7/","source_url":"https://arxiv.org/abs/2402.02342","text_available":true},{"id":"doi:10.1101/2024.02.22.581686","title":"MetaWorm: An Integrative Data-Driven Model Simulating <i>C. elegans</i> Brain, Body and Environment Interactions","date":"2024-02-26","section":"NeuroAI","quality":0.112333,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a26bc7d0fda3718e29040da4bcc69d633c78b62e148fd6043fd4e50714fc565b/","source_url":"https://doi.org/10.1101/2024.02.22.581686","text_available":true},{"id":"url:minedojo.org","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","date":"2022-06-17","section":"Agents, open-endedness, AGI","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/0a1b263777b8aec5e510481b45b7b4e11d45d7c127fd41dc37b5ff908f6420d2/","source_url":"https://minedojo.org/","text_available":false},{"id":"arxiv:2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","date":"2025-06-16","section":"Post-training","quality":0.353911,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5beb2ec6c7e6362f9d957219d7a205dd1adcc53f739acc0c7fd5f1f2bded4d83/","source_url":"https://arxiv.org/abs/2506.13585","text_available":true},{"id":"arxiv:2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","date":"2025-07-14","section":"LLMs: architectures, context, training","quality":0.17613,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7b25702c35f07446cea97d6a98afc489c8fdda54560c05fbeb1b3b139a9da622/","source_url":"https://arxiv.org/abs/2507.10524","text_available":true},{"id":"arxiv:2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","date":"2024-10-09","section":"Retrieval, embeddings, benchmarks","quality":0.31646,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f0a0c6321ec079098a36ad19b3900d77197a3af1f6bbf6eee8a083e5eb03d42e/","source_url":"https://arxiv.org/abs/2410.07095","text_available":true},{"id":"arxiv:2508.02513","title":"Modular Arithmetic: Language Models Solve Math Digit by Digit","date":"2025-08-04","section":"Reasoning and the \"physics\" of language models","quality":0.091161,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/83aede757707b76dc76fc15431a436e5dec05563a9f2f28ebcc650775c878bcc/","source_url":"https://arxiv.org/abs/2508.02513","text_available":true},{"id":"arxiv:2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","date":"2023-02-02","section":"Reasoning and the \"physics\" of language models","quality":0.040672,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/0fe1320410a5c35c29f2ac16d69a70adbf3c490670902745c2b4faf88460b5c7/","source_url":"https://arxiv.org/abs/2302.00923","text_available":true},{"id":"arxiv:2512.24695","title":"Nested Learning: The Illusion of Deep Learning Architectures","date":"2025-12-31","section":"Data, training, optimization","quality":-0.629827,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d19bf2367894704a701d0741e7db6d8b148719af1d634b55f5797aab5f617d06/","source_url":"https://arxiv.org/abs/2512.24695","text_available":true},{"id":"arxiv:2207.02098","title":"Neural Networks and the Chomsky Hierarchy","date":"2022-07-05","section":"LLMs: architectures, context, training","quality":0.297018,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/6c4e7406c7294ace52a03e4eede4ef1a31cd395dcde0958487fdbb546fa2c026/","source_url":"https://arxiv.org/abs/2207.02098","text_available":true},{"id":"doi:10.1371/journal.pcbi.1011005","title":"Neural spiking for causal inference and learning","date":"2023-01-01","section":"NeuroAI","quality":0.231816,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7ecb3e4c62d68dc77e8d7d5d489fb2bc708ced8e5cbddae81ea600413422e12f/","source_url":"https://doi.org/10.1371/journal.pcbi.1011005","text_available":true},{"id":"url:neuroevolutionbook.com","title":"Neuroevolution book","date":"2025-09-07","section":"Books","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/14e0f561c04bce8c6e98ee0b16071d0db6ba283c6587bba9b8d709fff8827635/","source_url":"https://neuroevolutionbook.com/","text_available":false},{"id":"arxiv:2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","date":"2023-07-12","section":"Data, training, optimization","quality":0.017146,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/fc9b59e6276d3fc1ebf8d77b30466c5047df876d0a884edfdfcdea124d6b76d6/","source_url":"https://arxiv.org/abs/2307.06440","text_available":true},{"id":"arxiv:2510.05491","title":"NorMuon: Making Muon more efficient and scalable","date":"2025-10-07","section":"Data, training, optimization","quality":0.070672,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c9ea441f9c2808077269690a88c1b1407189ac1cb03fbc0df89979a4d1d41b98/","source_url":"https://arxiv.org/abs/2510.05491","text_available":true},{"id":"url:oatllm.notion.site/oat-zero","title":"Oat-Zero: reproducing R1-Zero and analyzing self-reflection","date":"2025-03-21","section":"Post-training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e82b07c066d5c0a7cd37ee24c59ffaab40a3659b37607a86a541c7154c465a62/","source_url":"https://oatllm.notion.site/oat-zero","text_available":false},{"id":"arxiv:2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","date":"2020-05-04","section":"Reinforcement learning","quality":-0.419453,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/2ae228e6f0a418b4cd46f033b57c7452ba84a9c8cb985b198224186333c17d97/","source_url":"https://arxiv.org/abs/2005.01643","text_available":true},{"id":"arxiv:2512.13961","title":"Olmo 3","date":"2025-12-15","section":"LLMs: architectures, context, training","quality":0.225076,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8daa11a9729da9879a7e95c15d4eef3bab8579d2885a14102ed09db111221802/","source_url":"https://arxiv.org/abs/2512.13961","text_available":true},{"id":"arxiv:2508.05629","title":"On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification","date":"2025-08-07","section":"Post-training","quality":0.432404,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/0a17fccfeffa8a04070bb16903a7217d8adee804cf42e0cfc8dd128d3390474f/","source_url":"https://arxiv.org/abs/2508.05629","text_available":true},{"id":"openreview:ry_WPG-A-","title":"On the Information Bottleneck Theory of Deep Learning (Saxe et al.)","date":"2017-10-27","section":"Data, training, optimization","quality":-0.011319,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c10860ec07fd50dd9cabe10b023919ca199ae9bb2897cadbb523bbea39394ecf/","source_url":"https://openreview.net/forum?id=ry_WPG-A-","text_available":true},{"id":"arxiv:2508.11408","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","date":"2025-08-15","section":"Data, training, optimization","quality":0.16439,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/48594da2e3f2cdfeb17195dd033d047235fc4b4ffb65030800f64c6faedc4fbe/","source_url":"https://arxiv.org/abs/2508.11408","text_available":true},{"id":"arxiv:2212.09741","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","date":"2022-12-19","section":"Retrieval, embeddings, benchmarks","quality":0.51946,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b162d4a59ad6b25fd180e566615cf3dc2cd3a6c505f0421e15fd036236ad2ecd/","source_url":"https://arxiv.org/abs/2212.09741","text_available":true}],"next":"https://vinnik-dmitry07.github.io/favorite-papers/agents/catalog-0-11.html"}