Papers

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

Why we picked it

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。

Body

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。

Original · arXiv cs.AI

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.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include C3M, multimodal, agents, RAG.

Source attribution: curated from arXiv cs.AI (@Xueshu Chen, Yan Wang, Zihao Xue, Jiefu Li, Zhenfang Liu, Jayden Chen, Zhen Bi, Jungang Lou). Cross-source corroboration: 2 independent sources have covered this development (including openclaw), confirming industry-wide signal strength.