arXiv:2604.15877v1 Announce Type: new
Abstract: As LLM agents scale to long-horizon, multi-session deployments, efficiently managing accumulated experience becomes a critical bottleneck. Agent memory systems and agent skill discovery both address this…
arXiv:2604.14585v1 Announce Type: cross
Abstract: Prompt optimization in compound AI systems is statistically indistinguishable from a coin flip: across 72 optimization runs on Claude Haiku (6 methods $\times$ 4 tasks $\times$ 3 repeats), 49% score be…
arXiv:2604.11088v1 Announce Type: cross
Abstract: Developers increasingly guide AI coding agents through natural language instruction files (e.g., CLAUDE.md, .cursorrules), yet no controlled study has measured whether these rules actually improve agen…