Paper Without Code https://validator.w3.org/feed/docs/rss2.html Global Lyapunov functions: a long-standing open problem in mathematics, with symbolic transformers (AI for 3-body problem) Agents Thinking Fast and Slow: A Talker-Reasoner Architecture Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs (RAG for reasoning in agents) Boundless Socratic Learning with Language Games (a step toward AGI, maybe) Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search Let’s Verify Step by Step (must-read to build OpenAI o1) Thinking LLMs: General Instruction Following with Thought Generation (System 2 on CoT) Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Models (it is smarter than OpenAI o1!) Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement (Code for a Gödel AutoML XGBoost) Agent-Oriented Planning in Multi-Agent Systems (build your perplexity pro agent) Cognitive Architectures for Language Agents (How to use memory in reasoning) Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking (code of improved recursive CoT like in OpenAI o1) Thought of Search: Planning with Language Models Through the Lens of Efficiency Agent Workflow Memory Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning (Idea behind OpenAI o1) Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers Matryoshka Representation Learning Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents REAPER: Reasoning based Retrieval Planning for Complex RAG Systems (Amazon Rufus paper) CommunityKG-RAG: Leveraging Community Structures in Knowledge Graphs for Advanced Retrieval-Augmented Generation in Fact-Checking STaR: Self-Taught Reasoner Bootstrapping Reasoning With Reasoning About Accurate structure prediction of biomolecular interactions with AlphaFold 3 (300 lines of code for AlphaFold3) In-context Continual Learning Assisted by an External Continual Learner (No more RAG!) Improving Language Understanding by Generative Pre-Training (original GPT paper) Self-Discover: Large Language Models Self-Compose Reasoning Structures WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration Hello world! Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation Home Contact Blog Sample Page Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs (toward a better DeepSeek R1)