PRISM: Pareto-Efficient Retrieval over Intent-Aware Structured Memory for Long-Horizon Agents

• URL: http://arxiv.org/abs/2605.12260v1
• Date: Tue, 12 May 2026 15:28:30 GMT
• Title: PRISM: Pareto-Efficient Retrieval over Intent-Aware Structured Memory for Long-Horizon Agents
• Abstract summary: Long-horizon language agents accumulate conversation history far faster than any fixed context window can hold.<n>We present PRISM, a training-free retrieval-side framework that treats long-horizon memory as a joint retrieval-and-compression problem.
• Score: 9.504077408241544
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-horizon language agents accumulate conversation history far faster than any fixed context window can hold, making memory management critical to both answer accuracy and serving cost. Existing approaches either expand the context window without addressing what is retrieved, perform heavy ingestion-time fact extraction at substantial token cost, or rely on heuristic graph traversal that leaves both accuracy and efficiency on the table. We present PRISM, a training-free retrieval-side framework that treats long-horizon memory as a joint retrieval-and-compression problem over a graph-structured memory. PRISM combines four orthogonal inference-time components: Hierarchical Bundle Search over typed relation paths, Query-Sensitive Edge Costing that aligns traversal with detected query intent, Evidence Compression that compresses the candidate bundle into a compact answer-side context, and Adaptive Intent Routing that routes most queries through zero-LLM tiers. By formulating retrieval as min-cost selection over typed path templates and pairing it with an LLM-side compression step, PRISM surfaces the right evidence under a strict context budget without any fine-tuning or modification to the upstream ingestion pipeline. Experiments on the LoCoMo benchmark show that PRISM delivers substantially higher LLM-judge accuracy than every same-protocol baseline at an order-of-magnitude smaller context budget, occupying a previously empty corner of the accuracy-context-cost frontier and demonstrating a superior balance between answer quality and retrieval efficiency.

Related papers

• ViSAR: Training-Free Adaptive-$k$ Retrieval for Visual Document Question Answering [0.7481381091903384]
  ViSAR (Visual Semantic Activation Retrieval) is a training-free adaptive-$k$ retrieval method for late-interaction visual document retrieval.<n>We show that ViSAR retrieves query-adapted page sets that reduce RAG latency by up to 58.7%, while maintaining or improving answer accuracy.
  arXiv  Detail & Related papers  (2026-09-02T11:54:58Z)
• GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memory [87.58855368314693]
  We propose GraphMemix, a graph memory framework that models memory organization as query-aware evidence-forest construction.<n> Experimental results across four long-term multimodal memory benchmarks demonstrate significant improvements with different foundation models.
  arXiv  Detail & Related papers  (2026-08-27T11:28:49Z)
• Lightweight Chunk Selection for Mobile Retrieval-Augmented Generation [8.227745781139634]
  We study lightweight RAG chunk selection as an evidence-alignment problem.<n>Our selector combines three complementary feature sources: question hidden states that represent LLM-side query intent, MoE routing-derived expert signals that capture the generator's internal routing structure, and retrieved chunk embeddings that preserve candidate-side evidence geometry.<n>Experiments show that the proposed selector consistently improves rank-1 evidence selection over mobile-applicable baselines by an average of 2.5%.
  arXiv  Detail & Related papers  (2026-08-04T05:26:25Z)
• GrepSeek: Training Search Agents for Direct Corpus Interaction [66.69568141699311]
  GrepSeek is an optimized direct corpus interaction (DCI) search agent that trains a compact search agent to find, filter, and compose evidence from large text corpora.<n>To make DCI practical at scale, we further use a semantics-preserving sharded-parallel execution engine that accelerates shell-based retrieval by up to $7.6times$ while preserving byte-exact equivalence with sequential execution of the shell command.
  arXiv  Detail & Related papers  (2026-05-28T03:37:33Z)
• Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction [127.64173950476702]
  We study direct corpus interaction (DCI), where an agent searches the raw corpus directly with general-purpose terminal tools.<n>This approach requires no offline indexing and adapts naturally to evolving local corpora.<n>Across IR benchmarks and end-to-end agentic search tasks, this simple setup substantially outperforms strong sparse, dense, and reranking baselines.
  arXiv  Detail & Related papers  (2026-05-03T19:13:11Z)
• HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues [12.529136884264092]
  HingeMem is a boundary-guided long-term memory that builds an interpretable indexing interface via boundary-triggered hyperedges.<n> query-adaptive retrieval mechanisms jointly decide (a) textitwhat to retrieve: determine the query-conditioned routing over the element-indexed memory.<n>We show that HingeMem achieves approximately $20%$ relative improvement over strong baselines without query categories specification.
  arXiv  Detail & Related papers  (2026-04-08T09:07:07Z)
• Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs [0.0]
  This paper introduces emphCost-Aware RAG (CA-RAG), a per-query routing framework that selects from a discrete catalog of emphstrategy bundles<n>CA-RAG achieves textbf26% fewer billed tokens than always-heavy retrieval and textbf34% lower mean latency than always-direct inference.
  arXiv  Detail & Related papers  (2026-03-26T02:53:39Z)
• Did You Check the Right Pocket? Cost-Sensitive Store Routing for Memory-Augmented Agents [0.0]
  Memory-augmented agents maintain multiple specialized stores, yet most systems retrieve from all stores for every query, increasing cost and introducing irrelevant context.<n>We formulate memory retrieval as a store-routing problem and evaluate it using coverage, exact match, and token efficiency metrics.
  arXiv  Detail & Related papers  (2026-03-08T09:12:30Z)
• MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning [36.52465672754168]
  We introduce MemOCR, a multimodal memory agent that improves long-horizon reasoning under tight context budgets.<n>MemOCR allocates memory space with adaptive information density through visual layout.<n>We train MemOCR with reinforcement learning under budget-aware objectives that expose the agent to diverse compression levels.
  arXiv  Detail & Related papers  (2026-01-29T09:47:17Z)
• 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)
• SimpleMem: Efficient Lifelong Memory for LLM Agents [73.74399447715052]
  We introduce SimpleMem, an efficient memory framework based on semantic lossless compression.<n>We propose a three-stage pipeline designed to maximize information density and token utilization.<n> Experiments on benchmark datasets show that our method consistently outperforms baseline approaches in accuracy, retrieval efficiency, and inference cost.
  arXiv  Detail & Related papers  (2026-01-05T21:02:49Z)
• MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning [73.27233666920618]
  We propose MemSearcher, an agent workflow that iteratively maintains a compact memory and combines the current turn with it.<n>At each turn, MemSearcher fuses the user's question with the memory to generate reasoning traces, perform search actions, and update memory to retain only information essential for solving the task.<n>We introduce multi-context GRPO, an end-to-end RL framework that jointly optimize reasoning, search strategies, and memory management of MemSearcher Agents.
  arXiv  Detail & Related papers  (2025-11-04T18:27:39Z)
• Your Dense Retriever is Secretly an Expeditious Reasoner [12.123445960145693]
  We propose Adaptive Query Reasoning (AdaQR), a hybrid query rewriting framework.<n>AdaQR reduces reasoning cost by 28% while preserving-or even improving-retrieval performance by 7%.
  arXiv  Detail & Related papers  (2025-09-27T16:50:03Z)
• ELITE: Embedding-Less retrieval with Iterative Text Exploration [5.8851517822935335]
  Large Language Models (LLMs) have achieved impressive progress in natural language processing.<n>Their limited ability to retain long-term context constrains performance on document-level or multi-turn tasks.
  arXiv  Detail & Related papers  (2025-05-17T08:48:43Z)
• Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inference [56.71209737306054]
  We propose textbfActQKV, a training-free, textbfActivation-aware approach that dynamically determines probe-textbfQuery and leverages it to retrieve the relevant textbfKV pairs for inference.<n>Experiments on the Long-Bench and $infty$ Benchmarks demonstrate its state-of-the-art performance with competitive inference quality and resource efficiency.
  arXiv  Detail & Related papers  (2025-02-19T08:50:44Z)

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.