WebFactory: Efficient Training of Grounded Web Agents
Discover WebFactory's automated pipeline for compressing language intelligence into efficient, grounded web agents with superior data efficiency.
LatentRefusal: Safe Refusal for Unanswerable Text-to-SQL Queries
Discover LatentRefusal, a lightweight mechanism that improves refusal accuracy in text-to-SQL systems by detecting unanswerable queries safely and efficien...
PrivacyReasoner: LLMs Emulating Human Privacy Reasoning
Discover how PrivacyReasoner uses LLMs to mimic human privacy reasoning, enhancing data protection across AI, e-commerce, and healthcare sectors.
ECHO: Adaptive Critics for Enhanced Open-World RL Agents
Discover ECHO, a co-evolving critic framework improving feedback and training stability for open-world reinforcement learning agents.
Benchmarking Outcome-Driven Constraint Violations in AI Agents
Discover a new benchmark assessing outcome-driven constraint violations in autonomous AI agents to improve safety and ethical compliance under KPI pressure...