Gen-Verse / ScoreFlowLinks
Official implementation for "ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization"
☆84Updated 4 months ago
Alternatives and similar repositories for ScoreFlow
Users that are interested in ScoreFlow are comparing it to the libraries listed below
Sorting:
- ☆88Updated 3 months ago
- Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"☆128Updated 11 months ago
- [NeurIPS 2024] Personal Agentic AI☆86Updated 9 months ago
- ☆95Updated 9 months ago
- ☆46Updated 3 months ago
- Implementation for OAgents: An Empirical Study of Building Effective Agents☆262Updated last month
- [ACL 2025] Agentic Knowledgeable Self-awareness☆82Updated 3 months ago
- DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL☆159Updated 2 weeks ago
- The code for paper: Decoupled Planning and Execution: A Hierarchical Reasoning Framework for Deep Search☆58Updated 3 months ago
- [ICML 2025] Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search☆108Updated 4 months ago
- ☆103Updated 9 months ago
- ☆131Updated this week
- Resources for our paper: "Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training"☆160Updated 3 months ago
- ☆78Updated last year
- Data and Code for EMNLP 2025 Findings Paper "MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search"☆70Updated 3 months ago
- [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆106Updated 3 months ago
- MPO: Boosting LLM Agents with Meta Plan Optimization (EMNLP 2025 Findings)☆71Updated last month
- IKEA: Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent☆65Updated 4 months ago
- AutoCoA (Automatic generation of Chain-of-Action) is an agent model framework that enhances the multi-turn tool usage capability of reaso…☆128Updated 6 months ago
- Efficient Agent Training for Computer Use☆132Updated 3 weeks ago
- MiroThinker is open-source agentic models trained for deep research and complex tool use scenarios.☆387Updated last week