NUS, Princeton, Stanford & Oxford unveil Recuris: recursive self-improving agent memory without training
jiqizhixin · x · 2026-09-07
A team from NUS, Princeton, Stanford, and Oxford introduced Recuris (Recursive Experiential–Working Memory Evolution), targeting a fundamental flaw in agent memory for long-horizon tasks: memory updates driven only by downstream task scores can't pinpoint which component caused a failure, yielding coarse, untargeted updates that degrade further as reasoning traces grow.
Recuris is claimed to be the first agent architecture to apply recursive self-improvement inside the memory control layer. It maintains an experiential–working memory that continuously aligns accumulated experience with current execution needs, using three core technical breakthroughs to identify and fix specific memory components — with no training required.
The authors report it works across models from 3B open-source models up to Claude Opus 5 and GPT-5.6-Sol (post truncated; detailed results in the original).
More from coding & agent
- Dev runs a live show produced entirely by an agentic AI research team built on a wiki — SurvivedDravoswater · 2026-09-07
- Open-source Codex Skill turns one sentence into a holographic 3D card with Blender and Three.js — Promptmethus · 2026-09-07
- Jim Koppel: the vibe coder's way to understand code is running everything; the agentic engineer reads it — jimmykoppel · 2026-09-07
- OpenAI reportedly testing ChatGPT feature that mimics your writing style from emails and docs — VraserX · 2026-09-07
- Replit engineer moves all work in-house as new Max Mode cuts cost 65% via model routing — amasad · 2026-09-07
- Astra turns photogrammetry scan of old home into editable 3D scene, hinting inverse graphics has crossed the chasm — bilawalsidhu · 2026-09-07