This repository implements AutoThink in our paper: Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL
☆11May 20, 2025Updated last year
Alternatives and similar repositories for AutoThink-Preview
Users that are interested in AutoThink-Preview are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Improving Math reasoning through Direct Preference Optimization with Verifiable Pairs☆21Mar 20, 2025Updated last year
- [AAMAS'25] Code for "Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language Model"☆13May 27, 2025Updated last year
- [AAAI'25] Code for "In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning"☆14Jul 17, 2025Updated last year
- AutoThink is a reinforcement learning framework designed to equip R1-style language models with adaptive reasoning capabilities. Instead …☆54Oct 14, 2025Updated last year
- [NeurIPS 2025 D&B Track] MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research☆38Sep 8, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding, ECCV 2024☆11Jan 8, 2025Updated last year
- [NeurIPS 2024] Official pytorch implementation of SPLAT☆10Oct 14, 2024Updated 2 years ago
- ☆63Jun 7, 2025Updated last year
- personal info☆11Mar 23, 2024Updated 2 years ago
- ☆13Jul 14, 2024Updated 2 years ago
- Twitter Stance Dataset☆10Oct 29, 2020Updated 6 years ago
- ☆17Feb 9, 2026Updated 9 months ago
- PaperAudit-Bench: A Document-Level Benchmark and Multi-Agent Framework for Evidence-Aware Scientific Error Detection and Automated Peer R…☆20Sep 16, 2026Updated last month
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆56Nov 29, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Dynamic dual-granularity skill bank for agentic RL, jointly evolving policy and skills to improve long-horizon decision making in agentic…☆70Apr 1, 2026Updated 7 months ago
- Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding (ICLR 2023)☆22May 2, 2023Updated 3 years ago
- This is the source code of Part2Word: Learning Joint Embedding of Point Clouds and Text by Bidirectional Matching between Parts and Words☆16Mar 22, 2023Updated 3 years ago
- ☆26Aug 1, 2025Updated last year
- Code for "All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens"☆11Sep 11, 2025Updated last year
- Autonomous vehicle learn how to navigate efficiently at crossroad☆16Jan 31, 2018Updated 8 years ago
- [CVPR'24] MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding☆18Dec 13, 2024Updated last year
- ☆33Jul 2, 2026Updated 4 months ago
- A Reinforcement Learning to play StarCraft, written in PyTorch. Currently in research.☆11Mar 23, 2018Updated 8 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Official Implementation of UCOB: Credit-Aware On-Policy Bidirectional Self-Distillation for Learning to Utilize and Evolve Agentic Skills…☆35Sep 8, 2026Updated 2 months ago
- Reinforcement learning with docker and torcs☆19Aug 19, 2017Updated 9 years ago
- Dialogue Planning via Brownian Bridge Stochastic Process for Goal-directed Proactive Dialogue (ACL Findings 2023)☆21Nov 10, 2025Updated last year
- TRIAGE: Characterizing and auditing training data for improved regression (NeurIPS 2023)☆11Mar 14, 2024Updated 2 years ago
- ☆18Oct 9, 2024Updated 2 years ago
- B-STAR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners☆86May 21, 2025Updated last year
- ☆26Aug 23, 2024Updated 2 years ago
- ☆23Jul 5, 2024Updated 2 years ago
- Code accompanying paper "Models as Agents: Optimizing Multi-Step Predictions of Interactive Local Models in Model-Based Multi-Agent Reinf…☆15Dec 2, 2023Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICRA 2025] Towards Safe End-to-end Autonomous Driving via Online Map Uncertainty☆19Nov 14, 2024Updated last year
- ☆21Apr 2, 2024Updated 2 years ago
- ☆22Oct 21, 2022Updated 4 years ago
- [NeurIPS 2024] Can Language Models Learn to Skip Steps?☆22Jan 25, 2025Updated last year
- [ICLR2025 Spotlight] Advantage-Guided Distillation for Preference Alignment in Small Language Models☆27Feb 10, 2025Updated last year
- Visual Grounding with Multi-modal Conditional Adaptation (ACMMM 2024 Oral)☆26Jun 11, 2025Updated last year
- Official implementation of "Weakly-supervised positional contrastive learning: application to cirrhosis classification", MICCAI 2023☆11Dec 16, 2025Updated 10 months ago
Are these results useful?