Across five 100-task agent streams, sequential experience improves normalized reward by 16.9% in 14 of 15 model-domain combinations, but explicit skill maintenance matches pure in-context learning (0.602 vs 0.605) and weaker models build larger, less reusable skill pools.
Positive values indicate that the curated order places semantically related core skills closer together than expected under random ordering
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?
Across five 100-task agent streams, sequential experience improves normalized reward by 16.9% in 14 of 15 model-domain combinations, but explicit skill maintenance matches pure in-context learning (0.602 vs 0.605) and weaker models build larger, less reusable skill pools.