cross-task

Tag

Cards List
#cross-task

$\varepsilon$-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution

arXiv cs.AI · 18h ago Cached

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.

0 favorites 0 likes
#cross-task

SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution

Hugging Face Daily Papers · 2026-07-29 Cached

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.

0 favorites 0 likes
#cross-task

DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery

arXiv cs.LG · 2026-05-18 Cached

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.

0 favorites 0 likes
← Back to home

Submit Feedback