This work introduces \textsc{UpliftMem}, which learns memory retrieval from set-level execution uplift relative to the same executor without memory, and achieves the best success rates among evaluated baselines on the main evaluation sets.
Abstract
Large language model (LLM) agents reuse external memory to guide new tasks, but effective retrieval requires learning which memory sets improve execution. Such learning relies on costly outcome feedback: ordinary retrieval observes only executed sets, while evaluating alternatives requires additional rollouts. We introduce \textsc{UpliftMem}, which learns memory retrieval from set-level execution uplift relative to the same executor without memory. A theoretical analysis of how retrieval preferences restrict feedback coverage motivates targeted probing of alternative memory sets. Probe selection follows an expected value of sample information (EVSI) criterion, derived in closed form under a correlated Gaussian model, to allocate limited training rollouts according to their expected improvement in local retrieval decisions. The shared scorer is trained with a frozen executor and selects memory sets without test-time probes. Across ALFWorld, WebShop, and BigCodeBench, \textsc{UpliftMem} achieves the best success rates among evaluated baselines on the main evaluation sets. Controlled fixed-store and matched probe budget evaluations further demonstrate improved memory-use decisions and more effective use of execution feedback.
Long-term agent memory is shifting from predefined workflows toward learnable policies for memory construction and retrieval. Existing learning-based methods either optimize construction alone or combine retrieval-side online reinforcement learning (RL) with offline construction supervision, limiting co-adaptation betw...
Zhi-Qian Xia, Jie-Long Tang, Ling-An Zeng et al.· 0 citations
Agent memory enables large language model (LLM) agents to reuse past experiences without updating their parameters. However, semantic similarity alone does not guarantee memory usefulness: downstream performance depends on how memories are selected and presented to the agent. We propose MemComposer, a memory composer t...
Yi-Xuan Xie, Xue-Qiang Xu, Xin-Yi Fan et al.· 0 citations
SEDIMA is introduced, a persistent hierarchical insight memory for evolutionary search agents that distills raw traces into natural-language insights, clusters them by semantic similarity using attention-weighted centroids, and retrieves relevant guidance to condition future mutations, accumulating transferable knowled...
Amirhossein Abaskohi, Mahdi Mostajabdaveh, Zi-Rui Zhou· Proceedings of the Second Wo...· 0 citations
Attention with Routed Memory is proposed a novel KV caching structure that introduces a fully differentiable, fixed-size memory system organized as a hierarchical router that achieves superior performance and efficiency compared to fixed KV-caching approaches, while remaining efficient and scalable in terms of both mem...
Qiu-Hao Zeng, Jerry M. Huang, Peng Lu et al.· arXiv.org· 0 citations
Long-term agent memory requires recovering answer-relevant evidence dispersed across turns and sessions. Existing systems increasingly use structured memories and adaptive retrieval, yet often pass retrieved or expanded units directly to the reader, coupling memory addressing with evidence presentation and leaving the...
Shang-Ze Li, Yan-Yu Yao, De-Rong Xu et al.· 0 citations
Under a limited context budget, a long-term agent must recall not merely memories that are individually relevant, but evidence that is collectively sufficient for the current query. Conventional memory access retrieves, scores, and truncates memories, often spending multiple context slots on redundant facts while leavi...