{"total":415,"papers":[{"id":"arxiv:2503.00735","title":"LADDER: Self-Improving LLMs Through Recursive Problem Decomposition","date":"2025-03-02","section":"Post-training","quality":-0.008441,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/65b264030233bf2bcd17284eb9a521e6e38d4ee83eb7fec6587e4c047199f227/","source_url":"https://arxiv.org/abs/2503.00735","text_available":true},{"id":"arxiv:2402.16823","title":"Language Agents as Optimizable Graphs","date":"2024-02-26","section":"Agents, open-endedness, AGI","quality":0.294123,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/750bd3807bf9c9a9b5cd2d60cc14387431aec3fe8a3f942916ca5d8922b2a5b0/","source_url":"https://arxiv.org/abs/2402.16823","text_available":true},{"id":"arxiv:2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","date":"2023-02-27","section":"LLMs: architectures, context, training","quality":0.261634,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/fc11ce0896e97836324fcdf28bbcaf2c69f0e5e408a67265741605e450246035/","source_url":"https://arxiv.org/abs/2302.14045","text_available":true},{"id":"doi:10.1038/s41586-024-07522-w","title":"Language is primarily a tool for communication rather than thought","date":"2024-06-01","section":"Reasoning and the \"physics\" of language models","quality":-0.168117,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/60cfed62cd01166a972691a7c0da286223d861d23feebc5fadd3fa446168a33c/","source_url":"https://doi.org/10.1038/s41586-024-07522-w","text_available":true},{"id":"url:alexzhang13.github.io/blog/2026/harness","title":"Language model harnesses are compositional generalizers (Alex Zhang)","date":"2026-07-20","section":"Harness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d724c392cf5eb2db98d9a15e510d13b4220810c062a249c6a02ab86ee1895bb5/","source_url":"https://alexzhang13.github.io/blog/2026/harness/","text_available":false},{"id":"arxiv:2505.13763","title":"Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations","date":"2025-05-19","section":"Reasoning and the \"physics\" of language models","quality":-0.0936,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/95c4e7c49af162594458624b663c82546ad42167854a2235442954821ea69c65/","source_url":"https://arxiv.org/abs/2505.13763","text_available":true},{"id":"arxiv:2609.02737","title":"Language Models Can Control Their Own Attention","date":"2026-09-02","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d92e296c1a145dd5abf7d3efa06faf9f01243de35f8f197fc1e6221cba9fe442/","source_url":"https://arxiv.org/abs/2609.02737","text_available":true},{"id":"arxiv:2606.03982","title":"Language Models Compare Quantities Using Number-specific and Unit-specific Heuristics","date":"2026-06-02","section":"Reasoning and the \"physics\" of language models","quality":5.9e-05,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/48f07d03c9308ca8fb43ecd2ac22978f6dcbd4bc081056f022ca511711942dbf/","source_url":"https://arxiv.org/abs/2606.03982","text_available":true},{"id":"arxiv:2502.00873","title":"Language Models Use Trigonometry to Do Addition","date":"2025-02-02","section":"Reasoning and the \"physics\" of language models","quality":0.39366,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7766b2640c6b5ab53a295e8d60920cb2419bfbbd812810d9b35d4b7c323922ed/","source_url":"https://arxiv.org/abs/2502.00873","text_available":true},{"id":"arxiv:1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","date":"2019-04-01","section":"Data, training, optimization","quality":0.469974,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/2cea31116143e748e7497985367ddcf86a3da4aadb24ea47451b55947eedc9f0/","source_url":"https://arxiv.org/abs/1904.00962","text_available":true},{"id":"url:ai.meta.com/research/publications/large-concept-models-language-modeling-in-a-sentence-representation-space","title":"Large Concept Models: Language Modeling in a Sentence Representation Space","date":"2024-12-11","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a5cd322d52f1966361afb1d5225560e2d3ce4d22a117bd14cfa27ec669e09673/","source_url":"https://ai.meta.com/research/publications/large-concept-models-language-modeling-in-a-sentence-representation-space/","text_available":false},{"id":"arxiv:2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","date":"2021-12-15","section":"Retrieval, embeddings, benchmarks","quality":0.297587,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a98e608b4e34094fed75a118c0663f5f02f485081981cecc2bf3350181d61a51/","source_url":"https://arxiv.org/abs/2112.07899","text_available":true},{"id":"arxiv:2502.09992","title":"Large Language Diffusion Models","date":"2025-02-14","section":"LLMs: architectures, context, training","quality":0.498698,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a4863ed6f639560bd2feb6c66c13d1e3ac4cf42f8919a65c9818625cc6b6cde9/","source_url":"https://arxiv.org/abs/2502.09992","text_available":true},{"id":"arxiv:2605.22863","title":"Latent Cache Flow: Model-to-Model Communication Without Text","date":"2026-05-19","section":"LLMs: architectures, context, training","quality":-0.148425,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/eb6ed55f9fdbf8d212955b61ff74495737a2ecfacaa3645c7e4402b57e0c3e86/","source_url":"https://arxiv.org/abs/2605.22863","text_available":true},{"id":"arxiv:2310.04378","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","date":"2023-10-06","section":"Self-supervised learning and vision","quality":0.195723,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/16b9865215d555f17a2d1abc00c0915667686f20c49898f63872327a416690db/","source_url":"https://arxiv.org/abs/2310.04378","text_available":true},{"id":"arxiv:2608.13040","title":"Latent On-Policy Self-Distillation","date":"2026-08-13","section":"Post-training","quality":0.138951,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c2cfd504d6ca36ba88d75aba018620867d5fafd7433b03f3b2c9f51408422a02/","source_url":"https://arxiv.org/abs/2608.13040","text_available":true},{"id":"arxiv:2609.01117","title":"Latent Recurrent Thoughts: Recurrent Refinement of Proposed Latents for Reasoning with Frozen LLMs","date":"2026-09-01","section":"Reasoning and the \"physics\" of language models","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e9d4f61afc3930fa770d5ea53d3f43a5157fa4904fcdfaa514786e617905e20b/","source_url":"https://arxiv.org/abs/2609.01117","text_available":true},{"id":"arxiv:2407.00695","title":"Learning Formal Mathematics From Intrinsic Motivation","date":"2024-06-30","section":"Agents, open-endedness, AGI","quality":0.425409,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/68b19af6f86f72a1a7cedd8c0e476588d44d21a891d79fc640768859eac9a909/","source_url":"https://arxiv.org/abs/2407.00695","text_available":true},{"id":"arxiv:2606.18810","title":"Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards","date":"2026-06-17","section":"Post-training","quality":0.018354,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/9c11d77c6d08392f24aab79c8b45a3a3b0f4b743dd35e150a83ee7f6fa315248/","source_url":"https://arxiv.org/abs/2606.18810","text_available":true},{"id":"arxiv:2110.09485","title":"Learning in High Dimension Always Amounts to Extrapolation","date":"2021-10-18","section":"Data, training, optimization","quality":-0.296541,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/589d10ae90bda37ab0288fb5eadf87b368c249900944a0fe8b21a2f9bb267c01/","source_url":"https://arxiv.org/abs/2110.09485","text_available":true},{"id":"arxiv:2304.08467","title":"Learning to Compress Prompts with Gist Tokens","date":"2023-04-17","section":"Retrieval, embeddings, benchmarks","quality":-0.070542,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e77a0eef338c287982221a4a4770c18f85eb99a6d245af931d60a6ec9190ba69/","source_url":"https://arxiv.org/abs/2304.08467","text_available":true},{"id":"arxiv:2602.07755","title":"Learning to Continually Learn via Meta-learning Agentic Memory Designs","date":"2026-02-08","section":"Agents, open-endedness, AGI","quality":0.116631,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/4d0a0ea160495ea50583e0e24027b6085e2f430a44195e3053ba69cda8cc82ea/","source_url":"https://arxiv.org/abs/2602.07755","text_available":true},{"id":"arxiv:2601.16175","title":"Learning to Discover at Test Time","date":"2026-01-22","section":"Post-training","quality":0.274323,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5d0b45cbbc72945765e689cbfb7ac7e4e92dfbb764861b27682ac0744ef05b70/","source_url":"https://arxiv.org/abs/2601.16175","text_available":true},{"id":"arxiv:2505.19590","title":"Learning to Reason without External Rewards","date":"2025-05-26","section":"Post-training","quality":0.010191,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d8df33b706906a7abf4e660f54c75a81ffe2caaec8b0a10d1a6ad6ec63060832/","source_url":"https://arxiv.org/abs/2505.19590","text_available":true}],"next":"https://vinnik-dmitry07.github.io/favorite-papers/agents/catalog-0-9.html"}