RSM agent memory hits 83% of full-context quality at 32% token cost on a 4k budget
dair_ai · x · 2026-09-09
- dair-ai highlights RSM, a long-horizon agent memory method that separates two things usually collapsed into one: how memories merge on write, and how retrieved content is packed into the prompt. Setting: tight 2k–5k token budgets where full-context prompting is infeasible.
- Method: cosine-gated max-member merge on the write side plus an atom-aware grouped packer on the read side. At a 4k budget it reaches 83% of full-context quality at 32% of the token cost.
- Ablations attribute gains to both halves (+5.7 pts over online k-means for merging, +5.0 pts over flat packing); it reproduces on RealMem, beating Budget-RAG, Streaming-Proto and A-MEM.
More from coding & agent
- Fuzzing their Rust Postgres rewrite surfaced 20+ bugs in Postgres itself — DanielLockyer · 2026-09-09
- Switching AI from GUI to CLI mysteriously tanked this Mac's battery life — DanielLockyer · 2026-09-09
- Microsoft hosts MCP Live! 4-hour livestream with GitHub, AWS, Okta and Anthropic speakers — lee_stott · 2026-09-09
- Kent C. Dodds launches Kody to move between Claude Code, Cursor, and Codex without walled gardens — threepointone · 2026-09-09
- DaVinci Resolve 21.1 Called a Huge Update for Agentic Video Editing — gabrielchua · 2026-09-09
- Frost agent autonomously runs cross-GPU benchmarks with onchain reasoning — Michael_Moroz_ · 2026-09-09