# ConMem: Contribution-Aware Memory for Long-Horizon Manufacturing Inspection Logs

arXiv: https://arxiv.org/abs/2607.28126 · HTML: https://mlsanity.com/paper/2607.28126/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 36 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Builds on (most cited first, 13 of 13)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [SCM: Enhancing Large Language Model with Self-Controlled Memory Framework](https://mlsanity.com/paper/2304.13343/) (2023)
- [MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation](https://mlsanity.com/paper/2308.08239/) (2023)
- [Online Adaptation of Language Models with a Memory of Amortized Contexts](https://mlsanity.com/paper/2403.04317/) (2024)
- [ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents](https://mlsanity.com/paper/2603.00026/) (2026)

## Built on by (most cited first, 5 of 5)

- [Think-to-Personalize: Unifying Reasoning and Retrieval for User-Centric Personalized Dense Retrieval](https://mlsanity.com/paper/2608.18855/) (2026)
- [MemGuard: Persisting Verifier Signals for LLM-Agent Memory Governance](https://mlsanity.com/paper/2608.21867/) (2026)
- [When Images Look Right and Retrieve Wrong: Coverage-Guided Cross-Scale Re-Indexing for Knowledge-Faithful Generative Perception](https://mlsanity.com/paper/2608.20810/) (2026)
- [Modality Disentangled Learning for Incomplete Multimodal Emotion Recognition: A Primitive Memory Distillation Perspective](https://mlsanity.com/paper/2608.30563/) (2026)
- [A Guideline-Augmented Multi-Agent Framework for Schema-as-Code Biomedical Named Entity Recognition](https://mlsanity.com/paper/2610.02970/) (2026)

## Abstract (arXiv)

Long-horizon steel-equipment inspection requires reasoning over heterogeneous records accumulated across repeated inspection cycles. Existing retrieval-augmented generation systems treat historical logs as a static corpus and retain records without estimating their diagnostic value, failing to report early risk. To this end, we propose ConMem, a contribution-aware memory framework for LLM-assisted equipment inspection, supporting a human-in-the-loop early-risk screening system. Specifically, our ConMem first segments inspection logs into functional evidence units, then estimates each memory unit's contribution to downstream diagnosis through a Shapley-style estimation, and finally retains high-value evidence under a constrained memory budget. In experiments, we evaluate ConMem on real-world dataset and ConMem achieves 76.0% QA accuracy, exceeding the strongest directly comparable baseline. Relative to the naive 8K-context LLM baselines, it reduces the average number of input tokens by 88.2% and response time by 86.6%. Ablation studies also show that the functional-role-aware segmentation and contribution-based valuation are helping prioritize weak degradation signals for targeted field inspection. Practical deployments further confirm that ConMem retains the weak early signal across three inspection cycles, providing an early-stage seal-wear alert targeted for on-site inspectors.