Tag
The paper introduces ε-MemEvo, a framework for cross-task knowledge transfer in LLM-based program evolution, storing tactic memories as natural-language summaries and using an adaptive injection gate. It reports consistent gains on 8 optimization benchmarks with less than 1% computational overhead.
SkillRise is a unified reinforcement learning framework that enables LLM agents to learn and reuse skills across related, progressively challenging tasks, outperforming baselines by up to 8.5 percentage points on several benchmarks.
DrugSAGE is a framework that accumulates and reuses cross-task memory to build state-of-the-art drug discovery models efficiently, outperforming baseline agents by 10-30% on held-out tasks.