Similar Items: Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers
- Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents
- Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization
- SkillOS: Learning Skill Curation for Self-Evolving Agents
- Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation
- Synthetic Users, Real Differences: an Evaluation Framework for User Simulation in Multi-Turn Conversations
- Rose-SQL: Role-State Evolution Guided Structured Reasoning for Multi-Turn Text-to-SQL