The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks Paper • 2611.07461 • Published 1 day ago • 16
CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation Paper • 2504.00043 • Published Mar 30, 2025 • 10
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems Paper • 2504.01990 • Published Mar 31, 2025 • 304
Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks Paper • 2401.17263 • Published Jan 30, 2024 • 1
GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models Paper • 2402.03299 • Published Feb 5, 2024 • 1