ADaM-BJTU / AutoCoALinks
AutoCoA (Automatic generation of Chain-of-Action) is an agent model framework that enhances the multi-turn tool usage capability of reasoning models.
β128Updated 6 months ago
Alternatives and similar repositories for AutoCoA
Users that are interested in AutoCoA are comparing it to the libraries listed below
Sorting:
- β352Updated 3 months ago
- π§Tool-Star: Empowering LLM-brained Multi-Tool Reasoner via Reinforcement Learningβ262Updated 3 weeks ago
- β160Updated 8 months ago
- OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuningβ149Updated 9 months ago
- [ACL 2024] AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planningβ229Updated 8 months ago
- [ICLR 2025] Benchmarking Agentic Workflow Generationβ128Updated 7 months ago
- β209Updated last month
- Open Source Implementation of Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evoβ¦β85Updated 2 months ago
- Implementation for OAgents: An Empirical Study of Building Effective Agentsβ262Updated last month
- Scaling Deep Research via Reinforcement Learning in Real-world Environments.β610Updated 5 months ago
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agentsβ406Updated 2 months ago
- SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesisβ104Updated 4 months ago
- MPO: Boosting LLM Agents with Meta Plan Optimization (EMNLP 2025 Findings)β71Updated last month
- Resources for our paper: "Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training"β160Updated 3 months ago
- [ICLR 2025] The official implementation of paper "ToolGen: Unified Tool Retrieval and Calling via Generation"β158Updated 6 months ago
- β307Updated last year
- R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learningβ639Updated last month
- Awesome Agent Trainingβ231Updated 3 weeks ago
- β119Updated last week
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasksβ245Updated 4 months ago
- [ICML 2025] Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scaleβ263Updated 2 months ago
- [ACL 2025] Code and data for OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesisβ162Updated last month
- β103Updated 9 months ago
- MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Modelsβ49Updated 2 months ago
- β96Updated 9 months ago
- β169Updated 5 months ago
- [NeurIPS 2024 D&B Track] GTA: A Benchmark for General Tool Agentsβ124Updated 6 months ago
- β295Updated 4 months ago
- MiroThinker is open-source agentic models trained for deep research and complex tool use scenarios.β387Updated last week
- Implementation of "RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation".β246Updated last year