MemoraX pitches memory-model-driven recursive self-improvement for agents
Machine Heart reports that MemoraX AI has introduced a "Memory Model–Driven RSI" approach in which a dedicated memory model distills and updates procedural memory from an agent's execution traces and online feedback, while the agent system applies that experience to new tasks, forming a distill–apply–verify–update loop. The company says the method raised pass rates by more than 20% and cut the main coding agent's token use by more than 20% across 13 industrial long-horizon coding tasks (78 runs, over 335 hours total), and that 36 iterations on the financial benchmark FinRank lifted task accuracy from 33.33% to 73.33% with 96.49% evidence recall and roughly 98% lower cost than a Codex baseline. The piece also cites OpenAI's stated goal of automated AI researchers and Anthropic's claim that Claude already leads about 26% of its internal AI R&D work; all performance figures come from the vendor and have not been independently verified.
Whether long-term memory can turn each run's successes and failures into reusable experience is emerging as a key basis for agents' continued self-improvement, though the reported numbers are vendor-supplied.
机器之心 2026-10-10 18:23 北京
AI 正在从帮助人类完成任务,走向参与自身的研发与改进。
机器之心发布
近期,全球顶尖 AI 实验室正在密集释放一个信号:AI 正在从帮助人类完成任务,走向参与自身的研发与改进。
#MemoraX AI#OpenAI#Anthropic#Claude#Codex#Huawei#FinRank#Memory Model–Driven RSI