Researchers have introduced APEx, a novel framework designed to enhance deep research agents that use large language models with external tools. APEx organizes interaction history into instance-level memories and category-level procedural skills, which are then optimized through a three-stage training process. This approach allows for reward-guided skill distillation and enables agents to self-improve at test time without ground truth, by adapting online through skill-guided reinforcement learning. Experiments show APEx significantly outperforms existing methods, including GPT-5.4, on various benchmarks. AI
IMPACT This framework could lead to more capable AI agents for complex research tasks, improving efficiency and accuracy in scientific discovery.
RANK_REASON The cluster contains an academic paper detailing a new AI framework and its experimental results. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →