Similar Items: StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
- Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
- OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
- Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization
- Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
- SkillOS: Learning Skill Curation for Self-Evolving Agents
- Agentic-imodels: Evolving agentic interpretability tools via autoresearch