JingMog / THORLinks
Official Implementation of our paper "THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning".
☆27Updated 3 weeks ago
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 last month
- ☆38Updated this week
- ☆18Updated 2 months ago
- ☆26Updated 3 weeks ago
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment☆16Updated 9 months ago
- ☆45Updated last week
- A Recipe for Building LLM Reasoners to Solve Complex Instructions☆24Updated 2 months ago
- Code for "Language Models Can Learn from Verbal Feedback Without Scalar Rewards"☆42Updated 2 weeks ago
- ☆22Updated last year
- Emergent Hierarchical Reasoning in LLMs/VLMs through Reinforcement Learning☆36Updated last month
- ☆14Updated 9 months ago
- ☆50Updated 8 months ago
- [COLM 2025] "C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing"☆18Updated 6 months ago
- MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion (ACL 2025)☆29Updated 2 months ago
- [ACL 2025] Are Your LLMs Capable of Stable Reasoning?☆30Updated 2 months ago
- Code for Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation (EVOL-RL).☆38Updated last week
- JudgeLRM: Large Reasoning Models as a Judge☆39Updated 3 weeks ago
- [ICML 2025] Code for "R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts"☆16Updated 7 months ago
- ☆38Updated last month
- Official implementation of Self-Taught Agentic Long Context Understanding (ACL 2025).☆10Updated 3 weeks ago
- Tree Search for LLM Agent Reinforcement Learning☆127Updated 2 weeks ago
- Source code for our paper: "ARIA: Training Language Agents with Intention-Driven Reward Aggregation".☆23Updated 2 months ago
- Official repository for paper "DeepCritic: Deliberate Critique with Large Language Models"☆36Updated 3 months ago
- ☆18Updated 10 months ago
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆47Updated 3 months ago
- ☆16Updated last year
- MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer (EMNLP 2025)☆10Updated 5 months ago
- ☆31Updated 2 months ago
- TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs☆23Updated 3 weeks ago
- [NeurIPS 2025] Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models☆45Updated 2 weeks ago