Show HN: AI Agent Infrastructure and Memory Compaction Specifications
A Show HN submission titled "AI Agent Infrastructure and Memory Compaction Specifications" appeared alongside two new arXiv preprints on agent skills and agent memory, both announced as v1. The first preprint, SkillBuffBench (arXiv:2611.22017v1), introduces a benchmark for measuring what Agent Skills contribute across harnesses, models, skill access modes and memory, describing Agent Skills as file-based packages of procedural knowledge that a coding agent can discover and load on demand. The second, EvoDisco (arXiv:2611.22102v1), focuses on strategy discovery for evolving agent memory, arguing that how an agent's memory evolves during interaction matters as much as what is stored. The supplied material does not describe the contents of the Show HN post itself beyond its title, and neither
How this story unfolded
Key points6 items Model summary · ordered by when the evidence was published
- Point 01 11/17, 16:16
A Show HN post titled "AI Agent Infrastructure and Memory Compaction Specifications" was submitted; the material gives no further detail on its contents.
Based on 1 - Point 02 11/18, 13:00
SkillBuffBench is released as arXiv:2611.22017v1 under the new-announcement category.
Based on 1 - Point 03 11/18, 13:00
SkillBuffBench measures what Agent Skills contribute across harnesses, models, skill access modes and memory.
Based on 1 - Point 04 11/18, 13:00
Agent Skills are described as file-based packages of procedural knowledge that a coding agent can discover and load on demand.
Based on 1 - Point 05 11/18, 13:00
EvoDisco is released as arXiv:2611.22102v1 and addresses strategy discovery for evolving agent memory.
Based on 1 - Point 06 11/18, 13:00
EvoDisco's abstract holds that how an LLM agent's memory evolves during interaction is as important as what that memory contains.
Based on 1
ReportsBy publish time · newer further down
- November 17, 2026 · Tue
- November 18, 2026 · Wed
- +21h
EvoDisco: Strategy Discovery for Evolving Agent Memory
Original summary arXiv:2611.22102v1 Announce Type: new Abstract: Large language model agents accumulate experience in memory, and how that memory evolves during interaction is as important as what
arXiv cs.AI Original ↗ - +21h
SkillBuffBench: Measuring What Agent Skills Contribute across Harnesses, Models, Skill Access Modes and Memory
Original summary arXiv:2611.22017v1 Announce Type: new Abstract: Agent Skills, file-based packages of procedural knowledge that a coding agent can discover and load on demand, are now shipped by ev
arXiv cs.AI Original ↗ - Still developing · later reports will keep extending this axis