TergelMunkhbat / concise-reasoningLinks
Code for paper called Self-Training Elicits Concise Reasoning in Large Language Models
☆42Updated 6 months ago
Alternatives and similar repositories for concise-reasoning
Users that are interested in concise-reasoning are comparing it to the libraries listed below
Sorting:
- [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆108Updated 4 months ago
- ☆35Updated 5 months ago
- ☆40Updated 5 months ago
- ☆24Updated last year
- Process Reward Models That Think☆60Updated 2 weeks ago
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆108Updated 3 months ago
- [ACL 2025] A Generalizable and Purely Unsupervised Self-Training Framework☆71Updated 4 months ago
- [EMNLP'2025 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"☆66Updated 6 months ago
- SSRL: Self-Search Reinforcement Learning☆148Updated 2 months ago
- FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient LLM Reasoning☆53Updated 2 weeks ago
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆101Updated 2 months ago
- Verifiers for LLM Reinforcement Learning☆77Updated 6 months ago
- official implementation of paper "Process Reward Model with Q-value Rankings"☆64Updated 8 months ago
- Official repo of paper LM2☆47Updated 8 months ago
- [ACL 2025] Knowledge Unlearning for Large Language Models☆45Updated last month
- ☆219Updated 8 months ago
- ☆88Updated 4 months ago
- ☆50Updated 5 months ago
- ☆50Updated 8 months ago
- ☆101Updated 3 weeks ago
- ☆27Updated 4 months ago
- Systematic evaluation framework that automatically rates overthinking behavior in large language models.☆93Updated 5 months ago
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆83Updated 7 months ago
- Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"☆132Updated last year
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆178Updated 3 months ago
- Public code repo for paper "SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales"☆109Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated last year
- MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning☆104Updated 2 weeks ago
- [ACL 2025] Agentic Knowledgeable Self-awareness☆87Updated 4 months ago
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆79Updated 7 months ago