McGill-NLP / agent-reward-benchLinks
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
☆15Updated 2 weeks ago
Alternatives and similar repositories for agent-reward-bench
Users that are interested in agent-reward-bench are comparing it to the libraries listed below
Sorting:
- Verifiers for LLM Reinforcement Learning☆55Updated last month
- ☆24Updated 8 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆32Updated 2 months ago
- ☆64Updated 2 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆57Updated 9 months ago
- ☆19Updated 3 weeks ago
- Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)☆31Updated 2 months ago
- Reinforcing General Reasoning without Verifiers☆33Updated last week
- [ACL 2025] Are Your LLMs Capable of Stable Reasoning?☆25Updated 2 months ago
- ☆24Updated this week
- Code Implementation, Evaluations, Documentation, Links and Resources for Min P paper☆33Updated 2 months ago
- ☆16Updated 2 months ago
- ☆30Updated last week
- ☆38Updated this week
- Codebase for Instruction Following without Instruction Tuning☆34Updated 8 months ago
- The code implementation of MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models…☆34Updated last year
- The official implementation of Regularized Policy Gradient (RPG) (https://arxiv.org/abs/2505.17508)☆27Updated this week
- A testbed for agents and environments that can automatically improve models through data generation.☆24Updated 2 months ago
- ☆32Updated 4 months ago
- Process Reward Models That Think☆38Updated this week
- A repository for research on medium sized language models.☆76Updated last year
- ☆17Updated last month
- ☆79Updated 9 months ago
- ☆13Updated 5 months ago
- ☆45Updated 3 months ago
- Official Code Release for "Training a Generally Curious Agent"☆21Updated 2 weeks ago
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"☆26Updated 6 months ago
- ☆49Updated 6 months ago
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆47Updated last year
- This is the oficial repository for "Safer-Instruct: Aligning Language Models with Automated Preference Data"☆17Updated last year