Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models Significant performance improvements over previous SOTA methods: 11% on Game of 24, 20% on Geometric Shapes and 51% on Checkmate-in-One. repo: github.com/YangLing0818/b… abs: arxiv.org/abs/2406.04271

🤔why LLMs can only follow 1 thought template (e.g., CoT)? In our paper, LLMs can select their own thought process flexibly! Big improvement on agentic tasks! 🎉

Thought-Augmented Reasoning with LLMs Presents a thought-augmented reasoning approach, Buffer of Thoughts, to enhance the accuracy, efficiency, and robustness of LLM-based reasoning. It leverages a meta-buffer containing high-level thoughts (thought templates) distilled from

This paper claims that Llama3-8B+BoT (Buffer of Thoughts) has the potential to surpass Llama3-70B model. 🤯 'Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models' - Propose buffer-manager to dynamically update the meta-buffer, thus enhancing the capacity

Two new papers on self-improvement: paper 1 today ⬇️ In RISE, we build on online imitation to teach LLMs *how* to improve their own responses *sequentially*. w/ Llama2/3/Mistral, this gives solid +10-20% in 5 turns, outperforms parallel sampling! cohenqu.github.io/rise.github.io/ 🧵⬇️

Check out the amazing BFCL V2!

Check the new video arena! Pick your favorite video🚀

I will be at #NeurIPS2024 this week! Happy to chat about large scale RL for reasoning and agents!

Congrats to OpenAI on the impressive performance of o1 model! Seems o1 already achieves 76% on LoveCodeBench, how should we improve it to make it harder🤔🤔

Magic of RL! You don’t need super large models to develop such behavior! Congrats Jiayi Pan!

✨RL magic is in the air! Introducing DeepScaleR-1.5B-Preview—a fully open-source, 1.5B-parameter model trained with RL to surpass o1-preview for general math reasoning. 📜Blog: pretty-radio-b75.notion.site/DeepScaleR-Sur… 💻Github: github.com/agentica-proje…

With the success of LLM agents like OpenAI Operator, we are entering a new scaling era, but how do we train these agent models? We present InSTA, the largest training environment for LLM agents, containing live web navigation tasks for 150k diverse websites in multiple

LLMs for GPU kernel🌽generation have been getting Pop🍿ular since our preview last Dec; excited to announce 📢 our full paper 📃 for KernelBench! Turns out KernelBench is quite challenging 🧠 — frontier models outperform the PyTorch Eager baseline <20% of the time. More 🧵👇

What do developers 𝘳𝘦𝘢𝘭𝘭𝘺 think of AI coding assistants? In October, we launched Copilot Arena to collect user preferences on real dev workflows. After months of live service, we’re here to share our findings in our recent preprint. Here's what we have learned /🧵

🚨 NEW PAPER: "Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning"! 🤔 With all these long-reasoning LLMs, what are we actually optimizing for? Length penalties? Token budgets? We needed a better way to think about it! Website: cohenqu.github.io/mrt.github.io/ 🧵[1/9]

Proud to share what we have built! Tops the lmarena.ai leaderboard with only 17B parameters. Huge wing for the open source! Enjoy 😉

Introducing DeepCoder-14B-Preview - our fully open-sourced reasoning model reaching o1 and o3-mini level on coding and math. The best part is, we’re releasing everything: not just the model, but the dataset, code, and training recipe—so you can train it yourself!🔥 Links below: