SakanaAI / RLTLinks
Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.
☆122Updated this week
Alternatives and similar repositories for RLT
Users that are interested in RLT are comparing it to the libraries listed below
Sorting:
- Verifiers for LLM Reinforcement Learning☆60Updated 2 months ago
- SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning☆57Updated 2 months ago
- ☆50Updated 3 weeks ago
- accompanying material for sleep-time compute paper☆95Updated last month
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆68Updated 3 months ago
- Scaling Computer-Use Grounding via UI Decomposition and Synthesis☆79Updated last week
- ☆74Updated 2 months ago
- ☆65Updated 2 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆57Updated 9 months ago
- Official repo for Learning to Reason for Long-Form Story Generation☆63Updated 2 months ago
- Systematic evaluation framework that automatically rates overthinking behavior in large language models.☆90Updated last month
- How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training☆36Updated 2 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆41Updated last month
- ☆115Updated 4 months ago
- Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory☆62Updated last month
- The official repository of ALE-Bench☆78Updated last week
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆173Updated 5 months ago
- EvaByte: Efficient Byte-level Language Models at Scale☆102Updated 2 months ago
- ☆51Updated 7 months ago
- Official Repo for InSTA: Towards Internet-Scale Training For Agents☆42Updated this week
- Official Code Release for "Training a Generally Curious Agent"☆25Updated last month
- LLM reads a paper and produce a working prototype☆57Updated 2 months ago
- AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories☆18Updated last month
- Implementation of the paper: "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?"☆57Updated 6 months ago
- o1 Chain of Thought Examples☆33Updated 8 months ago
- Official repo of paper LM2☆41Updated 4 months ago
- Code for RATIONALYST: Pre-training Process-Supervision for Improving Reasoning https://arxiv.org/pdf/2410.01044☆33Updated 8 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆23Updated 2 months ago
- Official Code Repository for the paper "Distilling LLM Agent into Small Models with Retrieval and Code Tools"☆109Updated 2 weeks ago
- Code for ScribeAgent paper☆58Updated 3 months ago