Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses
[Sztuczna inteligencja] Autorzy: Zhaochen Yu, Yingcheng Wu, Zhenfei Yin i 5 więcej
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 fixed Meta-Agent turns that evidence into localized, validation-gated updates to Skill Memory that reshape execution and yield new evidence, forming a bounded recursive memory-evolution loop. Across four long-horizon benchmarks and ten models, Recuris improves task success in 35 of the 37 completed model-benchmark pairs, carrying frontier models…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja