ENGRAM paper bakes agent experience into LLM weights, deletes memory only after verified tests
_reachsumit · x · 2026-11-10
The ENGRAM framework (arXiv 2611.09472) consolidates stored agent experience into model weights while separating training admission from memory release. A demonstration-aware gate admits skills based on student mastery or sufficient successful teacher demonstrations, learning from action traces with context from an Engram Trace Graph (ETG). A verification gate then tests whether the updated model without episodic retrieval matches the base model with retrieval on reserved probes; only records passing both relative and absolute criteria are released, while failed skills stay retrievable. Experiments show consistent gains over frozen-weight ETG controls, and a held-out comparison finds verified release substantially shrinks the retrievable footprint while staying close to retain-all performance, beating immediate and budget-matched deletion.
More from coding & agent
- Fable 5.2 mined 1,400 Slack messages and 127 meeting notes, found 38 contradictions — every · 2026-11-10
- Inference, agents, databases: what software engineers must master as MCP turns SaaS into 'a database in a trench coat' — sh_reya · 2026-11-10
- Dev builds an entire MMO world in one day with Fable 5.2, saying stylized art is the real test for new models — TAbrodi · 2026-11-10
- Independent judge verifies Kurzgesagt clone: SSIM 0.9938, all 8 gates pass — RichardsonDx · 2026-11-10
- Agent clones 30s Kurzgesagt video in pure code: 720 frames, 99.4% frame match — RichardsonDx · 2026-11-10
- 'Vibe coded' becomes an insult — Willison, DHH and Linux kernel converge on one rule: own the review — alvelda · 2026-11-10