Similar Items: Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization
- Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers
- StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
- Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
- Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
- Reproducing Complex Set-Compositional Information Retrieval
- Multi-Level Narrative Evaluation Outperforms Lexical Features for Mental Health