LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural organization, learned retrieval strategies, or other complex operations. Is this complexity always necessary? We study Raw-RAG, a naive RAG baseline using dense retrieval and reranking over raw histo...
Zheng-Ye Bao, Shengtao Zhang, Hao-Kai Zhang et al.· 1 citation
MemQ is introduced, which applies TD ($\lambda$) eligibility traces to memory Q-values, propagating credit backward through a provenance DAG that records which memories were retrieved when each new memory was created.
TRACE is presented, a training-free layer that treats re-entry as an eligibility decision rather than a storage or retrieval operation, reconciling a departure checkpoint against absence-period updates, resolving explicit and implicit invalidation, and releasing a bounded Return View only when it covers the returning r...
Safety evaluations typically focus on individual agents, but interacting agents can spread harmful information and influence the environment in which later decisions are made. We study how collective failure changes with harmful-agent fraction and society size in a controlled financial agent society, where agents commu...
Le-Jun Zhang, Sarah Lu-Liang, Xin Jiang et al.· 0 citations
This work proposes MARA, which predicts future loss trajectories with conditional flow matching and coordinates compute nodes through a cooperative multi-agent autoregressive policy and reduces remaining-resource prediction error relative to weighted least squares.
Han-Ye Zhao, Mu-Ning Wen, Yong Yu et al.· 0 citations
Memory-Aware Propagation and Link Enforcement Guard, MAPLE-Guard, a memory-link guard for memory-enabled MAS, suggests that memory-aware link enforcement covers a gap left by prompt-level and topology-level defenses.
Wen-Jun Xiong, Yi-Jin Zhou, Jia-Qian Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.