Similar Items: Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents
- Dependency Parsing Across the Resource Spectrum: Evaluating Architectures on High and Low-Resource Languages
- Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers
- STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
- MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
- Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
- Stable Behavior, Limited Variation: Persona Validity in LLM Agents for Urban Sentiment Perception