Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs (toward a better DeepSeek R1)
- February 3, 2025
Yue Wang, Qiuzhi Liu, Jiahao Xu, Tian Liang, Xingyu Chen, Zhiwei He, Linfeng Song, Dian Yu, Juntao Li, Zhuosheng Zhang,…
Paper Without Code - A working code is worth a thousand words, so let LLM do it for you! “Paper without code” is an AI project to provide prototype implementations for classic and trending AI papers by using LLM code generation.
In-context Continual Learning Assisted by an External Continual Learner (No more RAG!)
- admin
- December 30, 2024
Saleh Momeni, Sahisnu Mazumder, Zixuan Ke, Bing Liu The paper, “In-context Continual Learning Assisted by an External Continual Learner,” introduces…
Boundless Socratic Learning with Language Games (a step toward AGI, maybe)
- admin
- December 29, 2024
Tom Schaul The paper “Boundless Socratic Learning with Language Games” by Tom Schaul offers a fascinating theoretical exploration of recursive…
Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
- admin
- December 29, 2024
Huanjin Yao, Jiaxing Huang, Wenhao Wu, Jingyi Zhang, Yibo Wang, Shunyu Liu, Yingjie Wang, Yuxin Song, Haocheng Feng, Li Shen,…
Thinking LLMs: General Instruction Following with Thought Generation (System 2 on CoT)
- admin
- November 9, 2024
Tianhao Wu, Janice Lan, Weizhe Yuan, Jiantao Jiao, Jason Weston, Sainbayar Sukhbaatar The research paper “THINKING LLMs: GENERAL INSTRUCTION FOLLOWING…
Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs (RAG for reasoning in agents)
- admin
- November 5, 2024
Liyi Chen, Panrong Tong, Zhongming Jin, Ying Sun, Jieping Ye, Hui Xiong The research paper “Plan-on-Graph: Self-Correcting Adaptive Planning of…
Cognitive Architectures for Language Agents (How to use memory in reasoning)
- admin
- October 25, 2024
Theodore R. Sumers, Shunyu Yao, Karthik Narasimhan, Thomas L. Griffiths The paper “Cognitive Architectures for Language Agents” by Theodore R.…
Global Lyapunov functions: a long-standing open problem in mathematics, with symbolic transformers (AI for 3-body problem)
- admin
- October 22, 2024
Alberto Alfarano, François Charton, Amaury Hayat The paper “Global Lyapunov functions: a long-standing open problem in mathematics, with symbolic transformers”…
Agents Thinking Fast and Slow: A Talker-Reasoner Architecture
- admin
- October 16, 2024
Konstantina Christakopoulou, Shibl Mourad, Maja Matarić The paper “Agents Thinking Fast and Slow: A Talker-Reasoner Architecture” from Deepmind presents an…
Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement (Code for a Gödel AutoML XGBoost)
- admin
- October 14, 2024
Xunjian Yin, Xinyi Wang, Liangming Pan, Xiaojun Wan, William Yang Wang The paper “GÖDEL AGENT: A SELF-REFERENTIAL FRAMEWORK FOR AGENTS…