C3M 提出跨会话多模态记忆维护方法,面向长程任务
C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks
一个开源的多模态记忆方案 C3M,专门解决智能体跨会话记不住事、记混事的问题,做长程任务的开发者可以看看它的索引加路由思路。
论文 C3M 解决长程任务中跨会话证据的保存与恢复问题,在有限的 query-blind 记忆预算内维护多模态记忆。
方法对持久化的文本-图像证据维持一个有界的活跃索引,通过 relation-aware 更新合并安全冗余,同时保留互补与相互冲突的记录。查询时由 budgeted routing 选取有用的索引页,并在固定 reader 预算下展开对应源证据。
该机制保留了时间区分和来源链接,支持可靠的下游推理,代码已在 GitHub 开源。
C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks
Long-horizon tasks require preserving and later recovering cross-session evidence under a bounded, query-blind memory budget. Existing compression can discard fine-grained visual cues or conflate semantically similar but incompatible observations. We present C3M, a cross-session multimodal memory organization that maintains a bounded active index over persistent source text-image evidence. Relation-aware updates consolidate safe redundancy while preserving complementary and incompatible records. At query time, budgeted routing selects useful index pages and expands their associated source evidence under a fixed reader budget. Together, these mechanisms establish a compact, provenance-preserving multimodal memory organization for cross-session long-horizon tasks, retaining temporal distinctions and source links required for reliable downstream reasoning. Code is available at https://github.com/HuzhouNLP/C3M.
本条情报归属 AITOP「论文」核心栏目,重点聚焦中国 AI 产业与国产大模型生态。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:C3M、多模态、智能体、RAG,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Xueshu Chen, Yan Wang, Zihao Xue, Jiefu Li, Zhenfang Liu, Jayden Chen, Zhen Bi, Jungang Lou),经 AITOP 多维评分管线结构化提炼。截至目前,全网已有 2 家独立信源对该事件进行交叉印证与跟进报道(含 openclaw 等),属于近期高关注度行业信号。
- openclaw09-24 02:58原文