Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full History

• URL: http://arxiv.org/abs/2606.09900v1
• Date: Fri, 05 Jun 2026 11:43:56 GMT
• Title: Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full History
• Abstract summary: Engram is a dual-process memory engine on a bi-temporal data model.<n>A fast write path appends episodes with no LLM on the critical path.<n>A hybrid read path fuses dense, lexical, graph, and recency/salience signals.
• Score: 2.5401434059780468
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-term memory is the missing layer for LLM agents: across sessions they forget, and the common workaround -- replaying the whole history into the prompt -- is expensive, slow, and, as distractors accumulate, less accurate. Most memory systems win on cost or latency but still lose to the full-context baseline on accuracy, and benchmark numbers are reported on inconsistent, non-reproducible harnesses, so one system appears at wildly different scores across sources. We present Engram, an open-source, dual-process memory engine on a bi-temporal data model. A fast write path appends lossless episodes with no LLM on the critical path; an asynchronous path extracts atomic (subject, predicate, object) facts, builds a bi-temporal knowledge graph, and resolves contradictions without an LLM call per fact -- invalidating, never deleting, so every fact keeps provenance and a supersession chain. A hybrid read path fuses dense, lexical, graph, and recency/salience signals, applies a point-in-time ("as-of") filter, and assembles a compact, provenance-tagged context. On the full 500-question LongMemEval_S, graded by the official category-specific judge, Engram's lean configuration -- answering from a ~9.6k-token retrieved slice, never the full history -- scores 83.6% vs. 73.2% for full-context (+10.4 points, McNemar p < 10^-6) at ~8x fewer tokens (9.6k vs. 79k), with 0/500 errored. The gain needs a hybrid read path: facts alone lose recall, while facts plus retrieved chunks recover detail. We also contribute a neutral, in-repo evaluation harness with the official judge baked in and the full-context baseline in every table, publish the raw per-question logs, and document the measurement-integrity pitfalls (truncation, home-grown judges, full-history leaks) that silently distort memory benchmarks. Every number ships with a command to reproduce it.

Related papers

• PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents [85.82624962221026]
  We introduce PARSER, which decouples reading from reasoning.<n>A bank of lightweight subagents each bound to a single chunk read the entire document in parallel.<n>On multi-hop QA with contexts ranging from 7K to 896K tokens, PARSER with a 4B backbone outperforms the strongest sequential memory baseline.
  arXiv  Detail & Related papers  (2026-09-06T16:19:01Z)
• Agent Zero Memory: Provenance-Aware Long-Term Memory for LLM Agents [3.6666917625778193]
  Agent Zero Memory is a provenance-aware long-term memory system.<n>It distils a user's conversations, files, and connected sources into three parallel memory systems.
  arXiv  Detail & Related papers  (2026-08-30T06:55:59Z)
• Hindsight Memory-PRM: Supervising Memory Management with Auditable Hindsight Credit [48.811961095386]
  Hindsight Memory-PRM exploits this audit trail twice.<n> offline to train an operation-conditioned memory-utility critic.<n>Online, where retrievals, citations, and one controlled deletion-and-reanswer per probe settle an intervention-calibrated entry-level presence credit.
  arXiv  Detail & Related papers  (2026-08-30T06:53:13Z)
• Ground Truth First: A Longitudinal Evaluation Instrument for Agent Memory, and the Tenure Crossover in Memory-Architecture Rankings [0.0]
  A seeded life-script sampler emits facts with validity intervals volatility classes, and source channels before any text exists.<n>A verifier confirms every planted fact and questions are instantiated mechanically from the script.<n>The synthetic, fictionalized corpus embeds features absent from the benchmarks we survey.
  arXiv  Detail & Related papers  (2026-07-24T04:19:45Z)
• 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)
• Eywa: Provenance-Grounded Long-Term Memory for AI Agents [0.0]
  Existing memory systems collapse source evidence, extracted facts, retrieved context, and answer policy into one opaque prompt path.<n>We present Eywa, a provenance-grounded memory architecture built around evidence before belief.
  arXiv  Detail & Related papers  (2026-05-29T02:56:35Z)
• WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction [72.1620416874118]
  Multimodal large language models are increasingly deployed as long-horizon agents.<n>Existing benchmarks measure recall over static dialogue, collapse memory into a single end-of-task accuracy, and reduce visual observations to captions.<n>We formulate multimodal agent memory as an Action-World Interaction Loop with an observable four-stage lifecycle.
  arXiv  Detail & Related papers  (2026-05-28T04:27:20Z)
• Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory [88.81430082035617]
  LLM agents require a memory system that can faithfully store, efficiently retrieve, and deeply reason over accumulated dialogue history.<n>We propose TriMem, which maintains three coexisting representation granularities, including raw dialogue segments anchored by source identifiers for storage fidelity.
  arXiv  Detail & Related papers  (2026-05-19T15:05:06Z)
• Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations [15.537674351419234]
  Context-manipulation attacks against deployed agents now actively exploit this gap.<n>We close it with a runtime verifier that maintains an explicit dependency graph.<n>Checking whether a continuation is supported reduces to a graph walk; retraction propagates through the same graph to flag exactly the conclusions that lose support.
  arXiv  Detail & Related papers  (2026-05-13T22:54:16Z)
• MEME: Multi-entity & Evolving Memory Evaluation [76.57263966646404]
  MEME defines six tasks spanning the full space defined by the multi-entity and evolving axes.<n> evaluating six memory systems spanning three memory paradigms on 100 controlled episodes.<n>We find that all systems collapse on dependency reasoning under the default configuration.
  arXiv  Detail & Related papers  (2026-05-12T17:55:10Z)
• WiCER: Wiki-memory Compile, Evaluate, Refine Iterative Knowledge Compilation for LLM Wiki Systems [0.0]
  We characterize the compilation gap across 17 RepLiQA domains (6,800 questions)<n>We propose WiCER, an iterative algorithm inspired by counterexample-guided abstraction refinement (CEGAR) that closes this gap.<n>An ablation across all 17 topics confirms that targeted diagnosis (+0.95), not generic pinning (+0.16), drives the gains.
  arXiv  Detail & Related papers  (2026-05-08T00:25:16Z)
• WorldDB: A Vector Graph-of-Worlds Memory Engine with Ontology-Aware Write-Time Reconciliation [0.0]
  WorldDB is a memory engine built on three commitments: (i) every node is a world, (ii) nodes are content-addressed and immutable, and (iii) edges are write-time programs.<n>On LongMemEval-s (500 questions, 115k-token conversational stacks), WorldDB with Claude Opus 4.7 as answerer achieves 96.40% overall / 97.11% task-averaged accuracy.
  arXiv  Detail & Related papers  (2026-04-20T16:30:53Z)
• Selective Memory for Artificial Intelligence: Write-Time Gating with Hierarchical Archiving [0.0]
  Parametric approaches compress knowledge into weights, precluding selective updates.<n>We introduce write-time gating that filters incoming knowledge objects using composite salience scores.
  arXiv  Detail & Related papers  (2026-03-16T23:06:44Z)
• Agentic Learner with Grow-and-Refine Multimodal Semantic Memory [50.81667005063605]
  ViLoMem is a dual-stream memory framework that constructs compact, schema-based memory.<n>It encodes visual distraction patterns and logical reasoning errors, enabling MLLMs to learn from their successful and failed experiences.
  arXiv  Detail & Related papers  (2025-11-26T18:55:08Z)
• WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia [59.96425443250666]
  Retrieval-augmented generation (RAG) has emerged as a promising solution to mitigate the limitations of large language models (LLMs) In this work, we conduct a comprehensive evaluation of LLM-generated answers to questions based on contradictory passages from Wikipedia. We benchmark a diverse range of both closed and open-source LLMs under different QA scenarios, including RAG with a single passage, and RAG with 2 contradictory passages.
  arXiv  Detail & Related papers  (2024-06-19T20:13:42Z)

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.