Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses
Quick summary
arXiv:2608.24876v1 Announce Type: new Abstract: Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation. We introduce Recuris, a recursive Experiential-Working Memory architecture for long-horizon agent harnesses, in which Working Memory tracks task progress and guides skill selection from Experiential Memory, grounding skill use in current needs rather than the full history. This coupling also turns execution into structured evidence that localizes failures to specific memory components. Across tasks, a
Key takeaways
- arXiv:2608.24876v1 Announce Type: new Abstract: Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation.
- We introduce Recuris, a recursive Experiential-Working Memory architecture for long-horizon agent harnesses, in which Working Memory tracks task progress and guides skill selection from Experiential Memory, grounding skill use in current needs rather than the full history.
- This coupling also turns execution into structured evidence that localizes failures to specific memory components.
Why it matters
“Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses” illustrates how changes in the AI ecosystem can affect products, workflows and user expectations together. Its lasting significance depends on measurable adoption, cost and safety outcomes.
Member comments