{"total":415,"papers":[{"id":"url:lilianweng.github.io/posts/2020-10-29-odqa","title":"Open Domain Question Answering (Lilian Weng)","date":"2020-10-29","section":"Retrieval, embeddings, benchmarks","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e1d9834a1aa6585269d7d2a8ec6f3db4dc87d14412778360bc484b06c4486bc3/","source_url":"https://lilianweng.github.io/posts/2020-10-29-odqa/","text_available":false},{"id":"arxiv:2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","date":"2024-06-06","section":"Agents, open-endedness, AGI","quality":-0.2417,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/13964b2db9a9f793d1fcae07ca83fbe09f65454214269cac56777cb8be423a4e/","source_url":"https://arxiv.org/abs/2406.04268","text_available":true},{"id":"arxiv:2606.06021","title":"OPRD: On-Policy Representation Distillation","date":"2026-06-04","section":"Post-training","quality":0.460296,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a16a9d7ea78c5748acc7f651c9a96663e0200d72e51d6a52c9528e1739a27d8d/","source_url":"https://arxiv.org/abs/2606.06021","text_available":true},{"id":"arxiv:1912.01683","title":"Optimal Policies Tend to Seek Power","date":"2019-12-03","section":"AI safety and consciousness","quality":0.047714,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7fe89b6251f3cacab8ed2ad8b728272f92e704949d342d0ab8b0ea97548860cb/","source_url":"https://arxiv.org/abs/1912.01683","text_available":true},{"id":"url:paperswithcode.com/paper/optimizing-millions-of-hyperparameters-by","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","date":"2019-11-06","section":"Data, training, optimization","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c5ceae5fd961be6d0bb1cd78bdf473d8b86954dc0615b3fb35ad9124be5e2643/","source_url":"https://paperswithcode.com/paper/optimizing-millions-of-hyperparameters-by","text_available":false},{"id":"url:semanticscholar.org/paper/4165542ba777ea63facc7ea9866f43ba63f054ae","title":"Orbifold Tutte embeddings (geometry processing)","date":"2015-08-01","section":"Other","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a0f48bc988a42cc9966bc9bfec8ebfe03afb4bcae7d8e1e41f320a8a2214be7d/","source_url":"https://www.semanticscholar.org/paper/4165542ba777ea63facc7ea9866f43ba63f054ae","text_available":false},{"id":"arxiv:2608.08311","title":"Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution","date":"2026-08-08","section":"Agents, open-endedness, AGI","quality":-0.116526,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/4b8f53ea59f810bf1717d78f1907b7596b91df2bec6751aba12accc8598c78e9/","source_url":"https://arxiv.org/abs/2608.08311","text_available":true},{"id":"doi:10.1073/pnas.1611835114","title":"Overcoming catastrophic forgetting in neural networks","date":"2017-03-14","section":"Data, training, optimization","quality":0.012852,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/849082368a44d06b93ef3ba95bcfddc6672b7a5e8064ad2b2d19601639266e8b/","source_url":"https://doi.org/10.1073/pnas.1611835114","text_available":true},{"id":"arxiv:1901.01753","title":"Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions","date":"2019-01-07","section":"Agents, open-endedness, AGI","quality":-0.0405,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/","source_url":"https://arxiv.org/abs/1901.01753","text_available":true},{"id":"arxiv:2503.16348","title":"Palatable Conceptions of Disembodied Being","date":"2025-03-20","section":"AI safety and consciousness","quality":-0.72055,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/00f41876b2b8852e1d5e080ecee9244ad7ccd7501df38c0527112912d3b462cf/","source_url":"https://arxiv.org/abs/2503.16348","text_available":true},{"id":"arxiv:2206.13477","title":"Parametrically Retargetable Decision-Makers Tend To Seek Power","date":"2022-06-27","section":"AI safety and consciousness","quality":-0.098112,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e47c3ca813aa251e657f4fd4b126d747e91e7518bcab8f7e9139a9cf5c8d95fb/","source_url":"https://arxiv.org/abs/2206.13477","text_available":true},{"id":"arxiv:2405.08007","title":"People cannot distinguish GPT-4 from a human in a Turing test","date":"2024-05-09","section":"Retrieval, embeddings, benchmarks","quality":-0.265154,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ec6cede2a895468a1dd14c92111b2a895f42c9eaab66f94918ef5340d1b183e1/","source_url":"https://arxiv.org/abs/2405.08007","text_available":true},{"id":"arxiv:2405.20541","title":"Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models","date":"2024-05-30","section":"Data, training, optimization","quality":0.16386,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/0633300a3d5ba43049372a7b551215c2d1a9443d02b8a74adf639b8a5d8476a8/","source_url":"https://arxiv.org/abs/2405.20541","text_available":true},{"id":"doi:10.1038/s41566-024-01394-2","title":"Photonic matrix multiplication lights up photonic accelerator and beyond","date":"2022-02-03","section":"Other","quality":-0.124899,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d76c7e42328d59edd381378f058bcbe3fa95ed88309ef2d703a9a5ca4b96d27b/","source_url":"https://doi.org/10.1038/s41566-024-01394-2","text_available":true},{"id":"arxiv:2305.13673","title":"Physics of Language Models: Part 1, Learning Hierarchical Language Structures","date":"2023-05-23","section":"Reasoning and the \"physics\" of language models","quality":0.451773,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a72219d4bd65d1e84ce31079b6c788d7e6c297e71d4b083af5d4cffccfdcff72/","source_url":"https://arxiv.org/abs/2305.13673","text_available":true},{"id":"arxiv:2407.20311","title":"Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process","date":"2024-07-29","section":"Reasoning and the \"physics\" of language models","quality":0.322996,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/de5db7bc6b929af401b5b83c845823505a7823c25987b0e455231d2e4fcec3e4/","source_url":"https://arxiv.org/abs/2407.20311","text_available":true},{"id":"arxiv:2309.14316","title":"Physics of Language Models: Part 3.1, Knowledge Storage and Extraction","date":"2023-09-25","section":"Reasoning and the \"physics\" of language models","quality":0.208192,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b87376d90e99d2bb590e1a02ed50a55c90881591ed7d3e00c3d5be2aaacbb2af/","source_url":"https://arxiv.org/abs/2309.14316","text_available":true},{"id":"arxiv:2309.14402","title":"Physics of Language Models: Part 3.2, Knowledge Manipulation","date":"2023-09-25","section":"Reasoning and the \"physics\" of language models","quality":0.28396,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/79b4d0b92a11dcf3b111e9d2d1b6bb3f516bebce7333326f65e6e583d6ff3cf2/","source_url":"https://arxiv.org/abs/2309.14402","text_available":true},{"id":"arxiv:2404.05405","title":"Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws","date":"2024-04-08","section":"Reasoning and the \"physics\" of language models","quality":0.359542,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/541683d3678177bb2800d37a49a2f541c8a2c81cf802eaefe8840fed359c540e/","source_url":"https://arxiv.org/abs/2404.05405","text_available":true},{"id":"openreview:wUU-7XTL5XO","title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change","date":"2022-06-21","section":"Reasoning and the \"physics\" of language models","quality":-0.296417,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/da39c89a33c7acabf5f152b7d25c596a91b3b44bb2dec90057cd739273338425/","source_url":"https://openreview.net/forum?id=wUU-7XTL5XO","text_available":true},{"id":"openreview:klU4737opt","title":"Position: LLMs can't jump","date":"2026-01-27","section":"Reasoning and the \"physics\" of language models","quality":-0.242361,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/67543c13943dbde84ba2294013023639fe44ae1c31fe1f2f1f59b623b885a3e3/","source_url":"https://openreview.net/pdf?id=klU4737opt","text_available":true},{"id":"arxiv:2304.06528","title":"Power-seeking can be probable and predictive for trained agents","date":"2023-04-13","section":"AI safety and consciousness","quality":-0.33811,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d7ff8707221493f94b2bbe97040d72c861160d33c5bfcce90eebf1e0ee3d3af8/","source_url":"https://arxiv.org/abs/2304.06528","text_available":true},{"id":"arxiv:2406.03445","title":"Pre-trained Large Language Models Use Fourier Features to Compute Addition","date":"2024-06-05","section":"Reasoning and the \"physics\" of language models","quality":0.375032,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/169a3e64467f1e0862508b86b2198187fc8eeb3ab114a47d2bd4caaea4a9ee2b/","source_url":"https://arxiv.org/abs/2406.03445","text_available":true},{"id":"url:github.com/primeintellect-ai/prime-agent","title":"Prime Agent: a self-improving RLM agent (Prime Intellect)","date":"2026-05-08","section":"Harness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/adc0cae9cb95aa146ec2de057eec3396aaa4ad014145497302e36230aefe7e3a/","source_url":"https://github.com/PrimeIntellect-ai/prime-agent","text_available":false}],"next":"https://vinnik-dmitry07.github.io/favorite-papers/agents/catalog-0-12.html"}