AlexCuadron / ThinkingAgent
Systematic evaluation framework that automatically rates overthinking behavior in large language models.
☆82Updated this week
Alternatives and similar repositories for ThinkingAgent:
Users that are interested in ThinkingAgent are comparing it to the libraries listed below
- ☆68Updated 4 months ago
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆140Updated this week
- ☆80Updated last month
- Scalable Meta-Evaluation of LLMs as Evaluators☆42Updated last year
- Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling☆95Updated 2 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆55Updated 7 months ago
- Code for Paper: Teaching Language Models to Critique via Reinforcement Learning☆84Updated last month
- ☆111Updated last month
- Code for EMNLP 2024 paper "Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning"☆53Updated 6 months ago
- ☆74Updated 2 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆168Updated 2 months ago
- DSBench: How Far are Data Science Agents from Becoming Data Science Experts?☆46Updated last month
- Implementation of the paper: "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?"☆53Updated 3 months ago
- The official repo for "LLoCo: Learning Long Contexts Offline"☆116Updated 9 months ago
- Long Context Extension and Generalization in LLMs☆50Updated 6 months ago
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate"☆131Updated last month
- Knowledge Unlearning for Large Language Models☆22Updated 3 weeks ago
- ☆54Updated this week
- B-STAR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners☆75Updated 2 months ago
- ☆24Updated 6 months ago
- Code for RATIONALYST: Pre-training Process-Supervision for Improving Reasoning https://arxiv.org/pdf/2410.01044☆32Updated 5 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆28Updated last week
- Framework and toolkits for building and evaluating collaborative agents that can work together with humans.☆70Updated last month
- Co-LLM: Learning to Decode Collaboratively with Multiple Language Models☆110Updated 10 months ago
- ☆41Updated 3 weeks ago
- SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning☆48Updated last month
- Code and Data for "Long-context LLMs Struggle with Long In-context Learning" [TMLR2025]☆102Updated last month
- ☆16Updated 2 months ago
- Flow of Reasoning: Training LLMs for Divergent Problem Solving with Minimal Examples☆80Updated last week
- ☆52Updated 3 weeks ago