MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents

• URL: http://arxiv.org/abs/2608.06745v1
• Date: Fri, 07 Aug 2026 03:13:43 GMT
• Title: MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents
• Abstract summary: Long-horizon agents rely on memory to reuse experiences, yet existing memory systems assume that evidence can be directly consumed through a fixed representation.<n>MemPrism is a task-conditioned relational memory framework that separates persistent experience storage from decision-time working memory.<n>MemPrism consistently improves the task performance, especially as trajectories become longer, while reducing memory token consumption.
• Score: 14.296334759650918
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-horizon agents rely on memory to reuse experiences, yet existing memory systems often assume that evidence can be directly consumed through a fixed representation. This leads to representation mismatch, where relevant information is available but not organized for the current decision. To this end, we propose MemPrism, a task-conditioned relational memory framework that separates persistent experience storage from decision-time working memory. MemPrism records interactions as the event stream and dynamically constructs relational views according to the current task context. A lightweight view policy selects the relation structure, evidence range, outcome condition, and granularity, while a deterministic composer and render transform historical facts into a temporary optical working-memory view for a frozen task policy. Experiments on long-horizon embodied and web-agent benchmarks show that MemPrism consistently improves the task performance, especially as trajectories become longer, while reducing memory token consumption. Furthermore, the learned view policy transfers across different VLMs without additional adaptation, demonstrating the effectiveness of task-conditioned relational views as a general memory interface for agents.

Related papers

• QUMem: Personalized Memory for Query-Conditioned User-State Inference in LLM Agents [24.465097221083777]
  textscQUMem is a structured memory framework for query-conditioned user-state inference.<n>textscQUMem achieves state-of-the-art performance on both PersonaMem and KnowU-Bench.
  arXiv  Detail & Related papers  (2026-08-17T06:34:24Z)
• CoEvo-Mem: Co-Evolving Retrieval Policy and Memory Bank for LLM Agents [12.963751758893594]
  We propose a closed-loop framework for co-evolving the retrieval policy and memory bank.<n>textbfCoEvo-Mem achieves state-of-the-art performance across seven diverse benchmarks.
  arXiv  Detail & Related papers  (2026-08-03T06:04:51Z)
• PMMC: Prospective Multimodal Memory Compilation for Long-Term LVLM Agents [19.297991318803508]
  Long-term memory is essential for LVLM agents to maintain consistency and integrate information across extended multimodal interactions.<n>We propose Prospective Multimodal Memory Compilation, a framework that shifts part of the memory reasoning process from query time to memory consolidation time.<n> Experiments on multimodal long-term memory benchmarks show that our method improves answer quality and visual evidence recall while reducing query-time token and latency costs.
  arXiv  Detail & Related papers  (2026-08-02T03:20:54Z)
• Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents [72.3752981234916]
  Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.<n>We present Memory as a Controlled Process (MemCon), a framework that models memory operations as a Markov Decision Process.<n>MemCon consistently outperforms multiple memory baselines by up to 15.2 points in task success while reducing token consumption by 5-20%.
  arXiv  Detail & Related papers  (2026-07-15T08:32:40Z)
• MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations [50.24315431387575]
  We introduce MemOps, a benchmark that reformulates conversational memory as a sequence of lifecycle operations.<n>MemOps represents each memory event with a structured trace specifying its trigger, target, scope, state transition, and supporting evidence.<n>Across long-context, retrieval-based, parametric and managed-memory systems, MemOps disentangles failure modes that final-answer accuracy alone conceals.
  arXiv  Detail & Related papers  (2026-07-14T15:33:44Z)
• Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents [51.30250860677378]
  We propose MRAgent, a framework that combines an associative memory graph with an active reconstruction mechanism.<n>Running on a Cue-Tag-Content graph, our active reconstruction mechanism integrates reasoning directly into memory access.<n>Experiments on the LoCoMo benchmark and LongMemEval benchmark demonstrate significant improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-06-04T11:29:46Z)
• MemCollab: Cross-Agent Memory Collaboration via Contrastive Trajectory Distillation [16.57908722474221]
  Large language model (LLM)-based agents rely on memory mechanisms to reuse knowledge from past problem-solving experiences.<n>Existing approaches typically construct memory in a per-agent manner, tightly coupling stored knowledge to a single model's reasoning style.<n>We found that naively transferring memory between agents often degrades performance, as such memory entangles task-relevant knowledge with agent-specific biases.<n>We propose MemCollab, a collaborative memory framework that constructs agent-agnostic memory by contrasting reasoning trajectories generated by different agents on the same task.
  arXiv  Detail & Related papers  (2026-03-24T14:05:47Z)
• MemGround: Long-Term Memory Evaluation Kit for Large Language Models in Gamified Scenarios [33.8882826707344]
  MemGround is a rigorous long-term memory benchmark grounded in rich, gamified interactive scenarios.<n>To comprehensively quantify both memory utilization and behavioral trajectories, we propose a multi-dimensional metric suite.
  arXiv  Detail & Related papers  (2026-03-23T02:57:39Z)
• MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks [55.145729491377374]
  Existing evaluations of agents with memory typically assess memorization and action in isolation.<n>We introduce MemoryArena, a unified evaluation gym for benchmarking agent memory in multi-session Memory-Agent-Environment loops.<n> MemoryArena supports evaluation across web navigation, preference-constrained planning, progressive information search, and sequential formal reasoning.
  arXiv  Detail & Related papers  (2026-02-18T09:49:14Z)
• AMA: Adaptive Memory via Multi-Agent Collaboration [54.490349689939166]
  We propose Adaptive Memory via Multi-Agent Collaboration (AMA), a novel framework that leverages coordinated agents to manage memory across multiple granularities.<n>AMA significantly outperforms state-of-the-art baselines while reducing token consumption by approximately 80% compared to full-context methods.
  arXiv  Detail & Related papers  (2026-01-28T08:09:49Z)
• Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory [89.65731902036669]
  Evo-Memory is a streaming benchmark and framework for evaluating self-evolving memory in large language model (LLM) agents.<n>We evaluate over ten representative memory modules and evaluate them across 10 diverse multi-turn goal-oriented and single-turn reasoning and QA datasets.
  arXiv  Detail & Related papers  (2025-11-25T21:08:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.