{"total":71,"papers":[{"id":"arxiv:2509.25239","title":"A Formal Comparison Between Chain of Thought and Latent Thought","date":"2025-09-25","section":"Reasoning and the \"physics\" of language models","quality":0.129176,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8399816be05fff6a7002f5c3439ec43ffe7b468424759b4cc70f5efc7739ea9e/","source_url":"https://arxiv.org/abs/2509.25239","text_available":true},{"id":"arxiv:2604.11791","title":"A Mechanistic Analysis of Looped Reasoning Language Models","date":"2026-04-13","section":"Reasoning and the \"physics\" of language models","quality":-0.159909,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ae8c682d5708c6c47d65c4eb540dd5bccb877c5e332852765507128d6d1b985d/","source_url":"https://arxiv.org/abs/2604.11791","text_available":true},{"id":"arxiv:2602.10416","title":"AI-rithmetic","date":"2026-02-11","section":"Reasoning and the \"physics\" of language models","quality":-0.399365,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a644c16d12f96071c95ea707eb5c5b3cc44be3dda2f9fe49a5f38735695fdad9/","source_url":"https://arxiv.org/abs/2602.10416","text_available":true},{"id":"arxiv:2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","date":"2023-04-28","section":"Reasoning and the \"physics\" of language models","quality":0.369634,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d7cd8c081ad54f2fdaa2211a4b49dc21f6ff2db7282e287546d210ef90e84323/","source_url":"https://arxiv.org/abs/2304.15004","text_available":true},{"id":"arxiv:2410.21272","title":"Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics","date":"2024-10-28","section":"Reasoning and the \"physics\" of language models","quality":0.602412,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/397b826ba289bd4f14f457562942cb092c38550a4c49451e95ffcc7b376c8cb0/","source_url":"https://arxiv.org/abs/2410.21272","text_available":true},{"id":"arxiv:2606.31779","title":"Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers","date":"2026-06-30","section":"Reasoning and the \"physics\" of language models","quality":0.291912,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/bf07d5c19e507d9ec91a48f9067e6c29fbe8965d001923e2de0e96da143c72e1/","source_url":"https://arxiv.org/abs/2606.31779","text_available":true},{"id":"arxiv:2505.21444","title":"Can Large Reasoning Models Self-Train?","date":"2025-05-27","section":"Reasoning and the \"physics\" of language models","quality":-0.120113,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/206224ca50098e0bdc230140722feec107cfc90c1cef2ed8d3ed52355ef56bca/","source_url":"https://arxiv.org/abs/2505.21444","text_available":true},{"id":"url:ai.googleblog.com/2022/11/characterizing-emergent-phenomena-in.html","title":"Characterizing emergent phenomena in LLMs (Google Research)","date":"2022-11-10","section":"Reasoning and the \"physics\" of language models","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/749249d7d689468b1404142d896fe5bd9048709780cc20f3a0f984a02bcc3aca/","source_url":"https://ai.googleblog.com/2022/11/characterizing-emergent-phenomena-in.html","text_available":false},{"id":"arxiv:2502.06807","title":"Competitive Programming with Large Reasoning Models","date":"2025-02-03","section":"Reasoning and the \"physics\" of language models","quality":-0.255672,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d1e6e9343805a99e3ba9032540f71dd4fc3436db1425ff988c9639e0c3641c8c/","source_url":"https://arxiv.org/abs/2502.06807","text_available":true},{"id":"arxiv:2301.06627","title":"Dissociating language and thought in large language models","date":"2023-01-16","section":"Reasoning and the \"physics\" of language models","quality":0.052829,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3791d7ed420be517ded1ee7ae5558cf6afa948ea5b841a76ec3da8a9134ec565/","source_url":"https://arxiv.org/abs/2301.06627","text_available":true},{"id":"arxiv:2212.09196","title":"Emergent Analogical Reasoning in Large Language Models","date":"2022-12-19","section":"Reasoning and the \"physics\" of language models","quality":0.120017,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f74e529a278203e2c144ab7400a343836d9549cf1ae4843c584408448ad3f5a9/","source_url":"https://arxiv.org/abs/2212.09196","text_available":true},{"id":"arxiv:2606.25010","title":"Emergent Capabilities Arise Randomly from Learning Sparse Attention Patterns","date":"2026-06-23","section":"Reasoning and the \"physics\" of language models","quality":0.029627,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f87db387bad54ae4fbc0589d2a702f78aeb0817b28f20844f6502bc552a89c2f/","source_url":"https://arxiv.org/abs/2606.25010","text_available":true},{"id":"arxiv:2605.21488","title":"Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning","date":"2026-05-20","section":"Reasoning and the \"physics\" of language models","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/48b3beca0f016a3683df4c6c71fc4be9f13a2c12c61d4ad17d1117c6139bb11e/","source_url":"https://arxiv.org/abs/2605.21488","text_available":true},{"id":"arxiv:2406.03689","title":"Evaluating the World Model Implicit in a Generative Model","date":"2024-06-06","section":"Reasoning and the \"physics\" of language models","quality":0.186581,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/41da4da8a33d9ab26af9650748067540eaf4cd386071ae0224a06450cdbb1fd0/","source_url":"https://arxiv.org/abs/2406.03689","text_available":true},{"id":"doi:10.1073/pnas.2520095123","title":"Evidence from formal logical reasoning reveals that the language of thought is not natural language","date":"2026-07-06","section":"Reasoning and the \"physics\" of language models","quality":-0.070856,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c9ba9811c4b4f1ea1fa65751f033bad4c2f6543f454b4d0d9e91a52abc6eb407/","source_url":"https://doi.org/10.1073/pnas.2520095123","text_available":true},{"id":"arxiv:2606.18206","title":"Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers","date":"2026-06-16","section":"Reasoning and the \"physics\" of language models","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/37ea2d83a92ece4ab3ba4434af71f291d1fdc5040676f75110210f40aad3b81a/","source_url":"https://arxiv.org/abs/2606.18206","text_available":true},{"id":"arxiv:2606.29150","title":"Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners","date":"2026-06-28","section":"Reasoning and the \"physics\" of language models","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8be1801f0f562711039ced2b42f324434c6ab829f544b8d736bc85405b64021b/","source_url":"https://arxiv.org/abs/2606.29150","text_available":true},{"id":"arxiv:2405.14838","title":"From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step","date":"2024-05-23","section":"Reasoning and the \"physics\" of language models","quality":-0.083004,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a242b6148f6f84466ce4315ac4937278586a242dd3f847146e142f3c7e27c39c/","source_url":"https://arxiv.org/abs/2405.14838","text_available":true},{"id":"arxiv:2605.19376","title":"Generative Recursive Reasoning","date":"2026-05-19","section":"Reasoning and the \"physics\" of language models","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/795bad9bb1b1a063090fbb925ba6e68bf30211de0ecffd75d56f858b28321ae7/","source_url":"https://arxiv.org/abs/2605.19376","text_available":true},{"id":"arxiv:2405.15071","title":"Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization","date":"2024-05-23","section":"Reasoning and the \"physics\" of language models","quality":0.461893,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1cd7fa83eca0b480c3bf9e2490c043b70e937777252a40b196ae7801a0620141/","source_url":"https://arxiv.org/abs/2405.15071","text_available":true},{"id":"openreview:hcQfTsVnBo","title":"Grokking Group Multiplication with Cosets","date":"2023-12-11","section":"Reasoning and the \"physics\" of language models","quality":0.433766,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/daa23510ca0765cf7cb802f4ab922f167481195d3b31bd012b5e4298470c342d/","source_url":"https://openreview.net/forum?id=hcQfTsVnBo","text_available":true},{"id":"arxiv:2506.21734","title":"Hierarchical Reasoning Model","date":"2025-06-26","section":"Reasoning and the \"physics\" of language models","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3604312101ff09ab9903e7d6a32c7b2b8a9a7ece6a9d145d04ea01c9d13ffa3a/","source_url":"https://arxiv.org/abs/2506.21734","text_available":true},{"id":"arxiv:2503.21676","title":"How do language models learn facts? Dynamics, curricula and hallucinations","date":"2025-03-27","section":"Reasoning and the \"physics\" of language models","quality":0.304138,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/2ef59e7bcfcfc0e4bab638835504ad8a0d2f50665a9797edc09e8628e9b3c0b6/","source_url":"https://arxiv.org/abs/2503.21676","text_available":true},{"id":"arxiv:2406.11813","title":"How Do Large Language Models Acquire Factual Knowledge During Pretraining?","date":"2024-06-17","section":"Reasoning and the \"physics\" of language models","quality":0.09754,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a7b36ce24eb2182e7f0bba96c0cddcfe6efe610b830d5e8ad8aac2b7d14696c0/","source_url":"https://arxiv.org/abs/2406.11813","text_available":true}],"next":"https://vinnik-dmitry07.github.io/favorite-papers/agents/catalog-5-2.html"}