MozerWang / AMPOLinks
[arxiv: 2505.02156] Adaptive Thinking via Mode Policy Optimization for Social Language Agents
☆35Updated 2 weeks ago
Alternatives and similar repositories for AMPO
Users that are interested in AMPO are comparing it to the libraries listed below
Sorting:
- Source code for our paper: "ARIA: Training Language Agents with Intention-Driven Reward Aggregation".☆18Updated last month
- Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆78Updated last month
- Official code implementation for the ACL 2025 paper: 'CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis'☆27Updated last month
- ☆132Updated last month
- Code for "CREAM: Consistency Regularized Self-Rewarding Language Models", ICLR 2025.☆22Updated 4 months ago
- A unified suite for generating elite reasoning problems and training high-performance LLMs, including pioneering attention-free architect…☆63Updated last month
- Official code for paper "SPA-RL: Reinforcing LLM Agent via Stepwise Progress Attribution"☆36Updated last week
- ☆64Updated 3 weeks ago
- RM-R1: Unleashing the Reasoning Potential of Reward Models☆113Updated 3 weeks ago
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment☆16Updated 6 months ago
- The demo, code and data of FollowRAG☆73Updated 2 weeks ago
- ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…☆31Updated last month
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆76Updated 5 months ago
- [ACL'25] We propose a novel fine-tuning method, Separate Memory and Reasoning, which combines prompt tuning with LoRA.☆67Updated last month
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆55Updated 7 months ago
- ☆20Updated 2 months ago
- SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis☆81Updated last month
- Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?☆24Updated 4 months ago
- Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆49Updated last month
- ☆46Updated 3 months ago
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆61Updated 6 months ago
- A Self-Training Framework for Vision-Language Reasoning☆80Updated 5 months ago
- [ACL 2024] The official codebase for the paper "Self-Distillation Bridges Distribution Gap in Language Model Fine-tuning".☆124Updated 8 months ago
- A comrephensive collection of learning from rewards in the post-training and test-time scaling of LLMs, with a focus on both reward model…☆50Updated last month
- [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.☆63Updated 8 months ago
- Large Language Models Can Self-Improve in Long-context Reasoning☆71Updated 7 months ago
- [ACL' 25] The official code repository for PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models.☆74Updated 5 months ago
- [ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style☆55Updated 2 weeks ago
- This the implementation of LeCo☆31Updated 5 months ago
- This is the repository of DEER, a Dynamic Early Exit in Reasoning method for Large Reasoning Language Models.☆157Updated last week