# Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents

Source: [Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents](<https://www.sota2.com/research/paper/6a28f37190966ade919c192b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-01T05:00:18.486Z

Authors: Qingcan Kang, Liu Mingyang, Shixiong Kai, Kaichao Liang, Tao Zhong, Mingxuan Yuan

Published: 2026-06-09T09:15:33.000Z

## Abstract

Long-horizon language agents accumulate observations, reasoning traces, and retrieved facts exceeding context windows, making memory retention a fundamental resource-allocation problem. Existing systems treat retention as local and do not model long-term consequences under observability constraints. To fill this gap, we formulate memory retention as a constrained stochastic optimization with budget feasibility, evidence utility, and delayed costs including miss, reacquisition, and stale penalties. We show this multi-step problem is NP-hard, making exact solution intractable. Moreover, deployment decisions must be made under partial observability. To address these challenges, we propose OSL-MR (Observability-Safe Learning for Memory Retention), a learning-augmented framework that enforces a strict separation between online-observable features and offline-available supervision. OSL-MR combines an evidence learner trained from realized evidence with a Mixed-Score heuristic that serves as a deployable online-safe baseline and an inductive prior. The policy learns query-conditioned evidence from interaction data and remains deployable under the same constraints. Experiments on LoCoMo and LongMemEval show OSL-MR outperforms recency-based, Generative Agents-style, and other heuristic baselines, especially under tight budgets. The Mixed-Score prior improves precision and recall, and sensitivity analysis shows robustness across cost settings. On small solvable instances, single-step optimization is insufficient to anticipate future demand shifts, while OSL-MR stays significantly closer to the dynamic-programming optimum, confirming the necessity of the sequential formulation and reinforcing our learning-guided approximation. These results establish constrained stochastic optimization and optimization-guided learning as a principled foundation for memory management in long-horizon agents.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Long-context Memory Management on LoCoMo (Precision, Recall, F1, Occupancy, Reward)](<https://www.sota2.com/research/sota/long-context-memory-management-on-locomo-precision-recall-f1-occupancy-reward.md>): Long-context memory management; Locomo; Precision: 31.3.

- [Long context memory management on LongMemEval](<https://www.sota2.com/research/sota/long-context-memory-management-on-longmemeval.md>): Long-context memory management; LongMemEval; Precision: 68.5.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.10616>)

[PDF](<https://arxiv.org/pdf/2606.10616.pdf>)