YerbaPage / MGDebuggerLinks
Multi-Granularity LLM Debugger
☆87Updated last month
Alternatives and similar repositories for MGDebugger
Users that are interested in MGDebugger are comparing it to the libraries listed below
Sorting:
- ☆54Updated last month
- [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆99Updated last month
- ☆108Updated 3 months ago
- Systematic evaluation framework that automatically rates overthinking behavior in large language models.☆91Updated 2 months ago
- ☆66Updated 4 months ago
- accompanying material for sleep-time compute paper☆99Updated 3 months ago
- SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning☆61Updated 3 weeks ago
- [ACL 2025] Agentic Knowledgeable Self-awareness☆77Updated last month
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆91Updated 6 months ago
- This repository contains popular code generation frameworks such as MapCoder, CodeSIM.☆56Updated last month
- II-Thought-RL is our initial attempt at developing a large-scale, multi-domain Reinforcement Learning (RL) dataset☆26Updated 4 months ago
- ☆96Updated 10 months ago
- ☆35Updated 2 years ago
- Easy to use, High Performant Knowledge Distillation for LLMs☆88Updated 3 months ago
- Data preparation code for CrystalCoder 7B LLM☆45Updated last year
- Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents☆125Updated last year
- The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆86Updated 2 weeks ago
- The official repo for “Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem”☆24Updated 2 months ago
- Code for Paper: Harnessing Webpage Uis For Text Rich Visual Understanding☆52Updated 7 months ago
- ☆37Updated 2 months ago
- ☆46Updated last year
- ☆40Updated 7 months ago
- ☆21Updated last week
- Scaling Computer-Use Grounding via UI Decomposition and Synthesis☆96Updated last month
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆173Updated 6 months ago
- ☆59Updated 8 months ago
- ☆53Updated 9 months ago
- Challenge LLMs to Reason About Reasoning: A Benchmark to Unveil Cognitive Depth in LLMs☆50Updated last year
- WebLINX is a benchmark for building web navigation agents with conversational capabilities☆156Updated 5 months ago
- Official repo for Learning to Reason for Long-Form Story Generation☆68Updated 3 months ago