paper-with-me

Papers

Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs

2026-09-09 · Ansuman Mullick, Eray Tüzün arxiv

Current LLM memory systems treat all personal facts identically, so stores grow without bound while retrieval precision degrades. The core challenge is lifecycle management: which memories should persist, which should be replaced, and at what rate, conditioned on the behavioral type of each fact. Fortunate Recall (FR) is a composable policy layer that classifies personal facts into a 10+1 behavioral ontology and applies category-specific lifecycle policies (differential temporal decay, slot-key supersession, event-time validity, and category-aware retrieval routing) as deterministic functions over LLM-extracted metadata. FR-Bank, our infrastructure-independent implementation, reaches a 76.9% pass rate on LifecycleBench, a new 516-question temporal-disambiguation benchmark, ahead of Mem0, A-MEM, Memory-R1, and MemoryOS (61% to 70.5%), and 75.2% on the full LongMemEval-S under the canonical Wu et al. judge protocol, so lifecycle policies impose no measurable cost on standard retrieval. A pre-registered ablation locates the gains: replacing the typed layer with three generic lifecycle primitives leaves correctness statistically unchanged (-1.7pp, 95% CI [-6.0, +2.7]), so the generic lifecycle metadata carries the correctness advantage, while the behavioral ontology carries calibration, halving downstream confabulation (12.0% vs 24.2%, p<0.001). End-to-end, FR-Bank cuts confabulation from Mem0's 45.1% to 22.4% over answered queries and from 32.2% to 13.0% over all queries while answering more of them correctly (31.2% vs 18.6%); the ranking replicates on the open-weight Kimi K2.5. The decomposition transfers to BEAM, an independently built benchmark: 46.8% correct vs Mem0's 32.9% over 280 questions, with the ontology's benefit concentrated in contradiction resolution and saturating near seven policy clusters. The ontology, benchmark, and code are released.

📄 PDF Abstract BibTeX arXiv:2609.10413

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Memory as Ontology: A Constitutional Memory Architecture for Persistent Digital Citizens

2026-03-05 · Zhenghui Li arxiv

Current research and product development in AI agent memory systems almost universally treat memory as a functional module -- a technical problem of "how to store" and "how to retrieve." This paper poses a fundamental ch…

StreamSoccer: Event-Driven Memory for Streaming Soccer Commentary

2026-08-20 · Chenxi Shao, Bozhong Wang, Jiaxin Huang, Zhao Liu 외 arxiv

Streaming video understanding requires models to causally update state as video arrives and organize growing history into semantic units that can evolve, persist, and be recalled under bounded computation and memory. Thi…

AMV-L: Lifecycle-Managed Agent Memory for Tail-Latency Control in Long-Running LLM Systems

2026-02-22 · Emmanuel Bamidele arxiv

Long-running LLM agents require persistent memory to preserve state across interactions, yet most deployed systems manage memory with age-based retention (e.g., TTL). While TTL bounds item lifetime, it does not bound the…

Attention-Based LSTM Network for COVID-19 Clinical Trial Parsing

2020-12-18 · Xiong Liu, Luca A. Finelli, Greg L. Hersch, Iya Khalil

COVID-19 clinical trial design is a critical task in developing therapeutics for the prevention and treatment of COVID-19. In this study, we apply a deep learning approach to extract eligibility criteria variables from C…

Rearchitecting Datacenter Lifecycle for AI: A TCO-Driven Framework

2025-09-30 · Jovan Stojkovic, Chaojie Zhang, Íñigo Goiri, Ricardo Bianchini arxiv

The rapid rise of large language models (LLMs) has been driving an enormous demand for AI inference infrastructure, mainly powered by high-end GPUs. While these accelerators offer immense computational power, they incur …