Dr. RTL: Advanced Autonomous RTL Optimization Framework
Discover Dr. RTL, an autonomous framework enhancing RTL optimization with realistic evaluation and self-improving tool-based methods for better chip design...
Trace2Skill: Transferable AI Agent Skills from Trajectories
Discover how Trace2Skill distills trajectory lessons into transferable skills, boosting AI agent performance across diverse tasks and models.
AdaRubric: Dynamic Task-Adaptive Rubrics for LLM Evaluation
Discover AdaRubric, a dynamic rubric system that adapts to tasks for accurate evaluation and improved training of LLM agents across diverse benchmarks.
AgentHER: Boost LLM Performance with Trajectory Relabeling
AgentHER enhances LLM agents by relabeling failed trajectories, improving task success rates and data efficiency in AI training.
AI Agents Achieve Stable Nash Equilibrium in Zero-Shot Games
Discover how reasoning AI agents avoid game-theoretic failures and reach stable Nash equilibria in zero-shot repeated games without fine-tuning.