This work proposes CALM, a conflict-aware lifecycle memory governance framework that decouples persistent memory preservation from query-time admission, and shows conflict-blocking and robustness analyses show CALM suppresses erroneous retrieved memories while retaining useful evidence.
Abstract
A memory can be outdated for present-day reasoning yet indispensable for reconstructing the past. Relevance-based retrieval overlooks this tension: semantic relevance, evidence-grounded validity, and query-specific eligibility are distinct. We propose CALM, a conflict-aware lifecycle memory governance framework that decouples persistent memory preservation from query-time admission. CALM converts heterogeneous records into evidence-grounded memory cells, updates validity and lifecycle states using support, conflict, and dependency signals, and admits query-appropriate evidence through training-free or learned gating informed by temporal applicability. Across LongMemEval-S and LoCoMo with Qwen and GPT backbones, CALM outperforms state-of-the-art baselines, achieving the best overall accuracy. Compared with simple filtering and reranking, query-conditioned admission further improves evidence selection. Conflict-blocking and robustness analyses show CALM suppresses erroneous retrieved memories while retaining useful evidence. Historical-reconstruction experiments demonstrate that preserving superseded records supports accurate earlier-state reasoning without compromising current-state answers.
This work introduces EGMEMORY, which formulates long-horizon multi-actor memory as a searchable state machine that separates persistent message-level evidence from an explicit active state.
Zi-Hao Lu, Zhi-Hang Yuan, Litu Ou et al.· arXiv.org· 1 citation
Long-horizon LLM agents require memory systems that preserve useful information across sessions and retrieve it when needed. Existing systems treat these as separate problems: memories are written prospectively with static importance scores that are never revised after use. This creates two coupled failure modes: conso...
Mayank Anand, Subham Raj, A. Jha et al.· 0 citations
Large language model (LLM)-based multi-agent systems increasingly rely on memory to transform execution trajectories into reusable procedural knowledge. Yet repeated retrieval also makes memory errors persistent: memory pollution arises when outdated, weakly supported, or spuriously successful procedures become recurri...
Ao-Li Tian, Jia-Long Liu, Da-Qi Zheng et al.· 0 citations
QEMem, a framework that reformulates memory utilization as the construction of query-specific evidence sets, shifting the focus from individual retrieval relevance to collective evidential support, achieves improved evidence coverage and strong performance on questions requiring cross-session evidence integration.
Shi-Xuan Li, Wei Yang, Pei-Yu Zhang et al.· 0 citations
Long-term memory supports agents across sessions. Repeated retrieval and write-back can let one historical claim occupy multiple retrieval positions and influence current answers without independent evidence. Existing work examines retrieval, updating, and question answering, leaving same-source record accumulation and...
Yufeng Li, Sheng Yao, Peng Zeng et al.· 0 citations
CoEM preserves potentially useful source excerpts verbatim in a pending set, allowing subsequent context to clarify their relevance before irreversible compression, and consistently improves long-context reasoning.