JingMog / THORLinks
Official Implementation of our paper "THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning".
☆27Updated last month
Alternatives and similar repositories for THOR
Users that are interested in THOR are comparing it to the libraries listed below
Sorting:
- The official code repository for the paper "Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions".☆15Updated 2 months ago
- ☆45Updated last month
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment☆16Updated 10 months ago
- ☆44Updated last month
- ☆17Updated 3 months ago
- Code for Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation (EVOL-RL).☆39Updated 3 weeks ago
- ☆23Updated last year
- A Recipe for Building LLM Reasoners to Solve Complex Instructions☆27Updated last month
- ☆30Updated last month
- Source code for our paper: "ARIA: Training Language Agents with Intention-Driven Reward Aggregation".☆24Updated 2 months ago
- ☆32Updated 3 months ago
- JudgeLRM: Large Reasoning Models as a Judge☆40Updated last month
- ☆38Updated 2 months ago
- Emergent Hierarchical Reasoning in LLMs/VLMs through Reinforcement Learning☆46Updated 2 weeks ago
- Official implementation of Self-Taught Agentic Long Context Understanding (ACL 2025).☆10Updated last month
- Code for "Language Models Can Learn from Verbal Feedback Without Scalar Rewards"☆51Updated last month
- [NeurIPS 2025] Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models☆47Updated last month
- Code for paper: Long cOntext aliGnment via efficient preference Optimization☆23Updated 3 weeks ago
- Official code implementation for the ACL 2025 paper: 'Dynamic Scaling of Unit Tests for Code Reward Modeling'☆25Updated 5 months ago
- [ACL 2025] Are Your LLMs Capable of Stable Reasoning?☆31Updated 3 months ago
- ☆50Updated 8 months ago
- dParallel: Learnable Parallel Decoding for dLLMs☆38Updated 3 weeks ago
- From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning.☆23Updated last month
- ☆17Updated 8 months ago
- ☆16Updated last year
- [COLM 2025] "C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing"☆18Updated 7 months ago
- ☆14Updated 10 months ago
- [ACL 2025] A Generalizable and Purely Unsupervised Self-Training Framework☆71Updated 5 months ago
- TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs☆23Updated last month
- ☆17Updated 10 months ago