Recuris

Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses

National University of Singapore  ·  Stanford University  ·  University of Oxford  ·  Princeton University

---

💡 Introduction

**Recuris** is a recursive self-improvement framework that **improves a long-horizon agent by evolving its memory instead of its weights or its prompt**. A frozen agent is paired with a **Skill Memory** `M = (E, W, ρ, C)`. A meta-agent reads structured execution traces, locates each failure in one component of that memory, and patches only that component. A deterministic validation gate then decides, on paired held-out evidence, whether the patch survives. Recuris has the following key features:

• State-grounded memory use. Working memory drives skill invocation, so retrieval is conditioned on verified task state rather than on a chat history that grows until the state is buried.
• Targeted memory evolution. Structured trajectories (w_t, E_t, a_t, o_t) locate a failure in a specific component, instead of nudging a monolithic prompt from outcom