AI 记不住长任务？这套记忆让成功率暴涨 32 分
现在的 AI 干长活会「失忆」:任务拖得越久，它越分不清自己做到哪、该调哪个技能。这篇给 AI 装了两层记忆——工作记忆盯着当前进度、经验记忆存着过往招数，让 AI 按当下需要挑技能，而不是翻完整本历史。更关键的是，它把每次执行变成「证据」，哪一步错了就精准修哪块记忆，修完再验证、再跑，形成一个自我进化的闭环。在 4 个长任务基准、10 个模型上，37 组测试里赢了 35 组，任务越长优势越大，最长任务上直接多拿 32.2 分，常见的长任务翻车率降了 80%。这不是你明天能用的产品，但它是「AI 能不能自己越用越强」这条路上一个实打实的里程碑。
📄 原文摘要(英文)
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 to SOTA-level task success: on tau-bench it adds +17.8 points to GPT-5.6 Sol and +15.6 to Claude Opus 5, taking Opus 5 to 87.9%, and +16.6/+13.5 points on Qwen3.6-27B/35B on SkillFlow. The advantage widens as the interaction horizon grows, to +32.2 points on the longest tasks, and common long-horizon failures fall by up to 80%. These results position recursively evolving memory as a scalable foundation for RSI, enabling agents to continuously transform accumulated experience into increasingly effective long-horizon behavior. Code: https://github.com/Gen-Verse/Recuris