Don't Ask the LLM to Track Freshness: A Deterministic Recipe for Memory Conflict Resolution

• URL: http://arxiv.org/abs/2606.01435v1
• Date: Sun, 31 May 2026 20:13:43 GMT
• Title: Don't Ask the LLM to Track Freshness: A Deterministic Recipe for Memory Conflict Resolution
• Abstract summary: We show that replacing the LLM-judgment answer pipeline with candidate-extraction plus Python max(serial) yields +10.8 points on FC-SH (gpt-4o-mini)<n>The recipe reaches 78.0% on FC-SH (gpt-4o-mini), 94.8% (gpt-4o), and 30.2% on FC-MH (gpt-4o-mini) via a per-hop deterministic extension of Self-Ask.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM-based memory systems increasingly maintain facts that evolve over time, where a recurring failure is conflict resolution: when a fact has multiple contradictory values, which should the agent return? MemoryAgentBench (MAB; Hu et al., 2026) makes this explicit in its FactConsolidation task: facts are numbered, the counterfactual has the higher serial, and agents are told newer facts have larger serials. Yet every published system underperforms: HippoRAG-v2 reaches 54% on single-hop (FC-SH), BM25 48%, Mem0 18%, and the temporal KG Zep/Graphiti just 7%. Multi-hop is near-unsolved (at most 7% across 22 systems). We argue the bottleneck is the assembly step: baselines leave conflict resolution to LLM-mediated retrieval or generation rather than version-aware aggregation. A matched-setup comparison (same backbone, retrieval, chunking, TOP_K) shows that replacing the LLM-judgment answer pipeline with candidate-extraction plus Python max(serial) yields +10.8 points on FC-SH (gpt-4o-mini), widening from +8 at 6K to +21 at 262K. This is a whole-pipeline effect (resolver, prompt, format, and temperature vary jointly); isolating the resolver is future work. The recipe reaches 78.0% on FC-SH (gpt-4o-mini), 94.8% (gpt-4o), and 30.2% on FC-MH (gpt-4o-mini, rising to 51.5% with gpt-4o) via a per-hop deterministic extension of Self-Ask. At matched-262K, it beats HippoRAG-v2 by +28 points and the best published FC-MH result by +20. The implication is corrective for the subfield: the bottleneck on conflict resolution is assembly (post-retrieval aggregation), not storage. A LongMemEval knowledge-update check shows the mechanism ports from max(serial) to max(timestamp) but only ties LLM judgment (57.8% vs 64.4%, n=45): deterministic aggregation is the right primitive for current-value conflicts and must be composed with question-type-aware handling for broader memory QA.

Related papers

• LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning Tasks [3.789882665982407]
  Multi-agent large language model (LLM) systems can improve reasoning by spending more computation.<n>We isolate this decision by running every problem under four protocols while holding the solver fixed within each setting.
  arXiv  Detail & Related papers  (2026-08-14T22:35:37Z)
• The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Context [45.88028371034407]
  We report a controlled case study in code repair, not a new phenomenon.<n>We toggle one flag (one-chunk-perfile deduplication) on an otherwise identical stack.<n>We map where it holds: it reverses on a lexical BM25 (3.2pp, significant cross-paradigm interaction)<n>We show that at a tight fixed budget, do not hard-deduplicate by file, and A/B packing policies against the task, not the metric flag was tuned.
  arXiv  Detail & Related papers  (2026-08-14T19:22:50Z)
• Oracle Gap and Signal Fidelity: A Fixed-Pool Diagnostic for Test-Time Collaboration [8.515185888009833]
  Test-time collaboration is often credited with improving LLM reasoning, yet its gains are uneven and sometimes negative.<n>For a fixed candidate pool, we decompose a selector or verifier's net gain into measurable factors.<n>This reframes collaboration as a candidate-selection problem rather than as an intrinsic property of a multi-agent topology.
  arXiv  Detail & Related papers  (2026-07-20T04:09:19Z)
• MemDelta: Controlled Baselines and Hidden Confounds in Agent Memory Evaluation [8.38765074765613]
  Agent memory systems are increasingly evaluated against RAG and full-context baselines.<n> reported gains often mix changes in the memory method with changes in the language model, embedding model, or retrieval pipeline.<n>We present MemDelta, a controlled evaluation protocol that varies one component at a time on LongMemEval-S (500 questions, 50+ sessions, three model families.
  arXiv  Detail & Related papers  (2026-06-29T07:51:22Z)
• SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale [54.70985426016736]
  We present SkillDAG, which models inter-skill relationships as a typed directed graph.<n>Each search returns vector matches, typed-edge neighbors, and conflict signals, and a propose-then-commit protocol lets the agent register execution-backed edges.<n>On ALFWorld and SkillsBench with MiniMax-M2.7, SkillDAG reaches 67.1% success and 27.3% reward.
  arXiv  Detail & Related papers  (2026-06-02T02:45:21Z)
• Sequential Consensus for Multi-Agent LLM Debates: A Wald-SPRT compute governor with calibration-based failure detection [0.0]
  Multi-agent debate improves factuality and reasoning, but most recipes pick a fixed round count.<n>We adapt Wald's Sequential Probability Ratio Test (SPRT) as a plug-in compute governor for LLM debates.<n>On GSM8K the rule stops in 1.01 average rounds (4.06 LLM calls) at 97.0% accuracy vs 99.0% for fixed-5 debate at 15 calls: a 3.7x call reduction at -2pp accuracy.<n>On MMLU the calibrated KL collapses to about 0 and the rule caps on 99.5% of items at 2.1x cost.
  arXiv  Detail & Related papers  (2026-05-18T23:43:12Z)
• The Range Shrinks, the Threat Remains: Re-evaluating LLM Package Hallucinations on the 2026 Frontier-Model Cohort [51.56484100374058]
  Spracklen et al. showed that code-generating large language models hallucinate package names that do not exist on PyPI or npm.<n>We measure hallucination rates across 199,845 paired Python and JavaScript prompts validated against PyPI and npm master lists.<n>We identify a set of 127 package names (109 on PyPI, 18 on npm) that all five evaluated models invent identically.
  arXiv  Detail & Related papers  (2026-05-16T16:08:52Z)
• Measuring Maximum Activations in Open Large Language Models [60.3514350516308]
  We measure global and layerwise maxima on 27 checkpoints from 8 open families spanning dense, MoE, vision-language, intermediate-training, and instruction-tuned variants.<n>We conclude that maximum activation magnitude is a model property tied to family, architecture, and training stage - not a simple byproduct of size.
  arXiv  Detail & Related papers  (2026-05-15T03:31:51Z)
• OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation [53.88666485159289]
  We introduce OpenDeepThink, a population-based test-time compute framework that selects via pairwise Bradley-Terry comparison.<n>OpenDeepThink raises Gemini 3.1 Pro's effective Codeforces Elo by +405 points in eight sequential LLM-call rounds.<n>We release CF-73, a curated set of 73 expert-rated Codeforces problems with International Grandmaster annotation and 99% local-evaluation agreement against the official verdict.
  arXiv  Detail & Related papers  (2026-05-14T17:57:40Z)
• MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs [47.66730296440261]
  We introduce MemQ, which propagates credit backward through a provenance DAG that records which memories were retrieved when each new memory was created.<n>Across six benchmarks, MemQ achieves the highest success rate on all six in generalization evaluation and runtime learning.<n>We further study how $$ and $$ interact with the EC-MDP structure, providing principled guidance for parameter selection and future research.
  arXiv  Detail & Related papers  (2026-05-08T18:30:24Z)
• Correct Code, Vulnerable Dependencies: A Large Scale Measurement Study of LLM-Specified Library Versions [52.50730821321986]
  We present the first large-scale measurement study of version-level risk in large language models (LLMs)<n>We evaluate 10 LLMs on PinTrace, a curated benchmark of 1,000 Stack Overflow programming tasks.<n>Our findings reveal LLM version selection as a first-class, previously overlooked risk surface in LLM-based development.
  arXiv  Detail & Related papers  (2026-05-07T13:52:59Z)
• Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs [48.83701310501069]
  Large language models (LLMs) show strong potential for neural architecture generation.<n>Existing approaches produce complete model implementations from scratch.<n>We propose Delta-Code Generation, where fine-tuned LLMs generate compact unified diffs.
  arXiv  Detail & Related papers  (2026-05-06T13:32:05Z)
• The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation [6.290180827867576]
  Hypernetwork-based methods internalize a document into an LLM's weights in a single forward pass.<n>When the document contradicts pretraining knowledge, accuracy collapses to 46.4% on the deepest facts.<n>We show the failure is a magnitude problem rather than a representational one.
  arXiv  Detail & Related papers  (2026-04-26T14:59:14Z)
• vstash: Local-First Hybrid Retrieval with Adaptive Fusion for LLM Agents [0.0]
  We present **vstash**, a local-first document memory system that combines vector similarity search with fulltext keyword matching.<n>All data resides in a single file using sqlite-vec for approximate nearest neighbor search and FTS5 for keyword matching.
  arXiv  Detail & Related papers  (2026-04-16T19:22:58Z)
• Cooperative Memory Paging with Keyword Bookmarks for Long-Horizon LLM Conversations [2.6382975801439836]
  We propose cooperative paging: segments are replaced with minimal keyword bookmarks, and the model is given a recall() tool to retrieve full content on demand.<n>On the LoCoMo benchmark, cooperative paging achieves the highest answer quality among six methods -- outperforming truncation, BM25, word-overlap retrieval, a search-tool baseline, and full context.<n>We then study the paging design space with a 5x4 ablation over boundary strategies and eviction policies (3,176 synthetic probes, 1,600 LoCoMo probes)
  arXiv  Detail & Related papers  (2026-04-14T07:06:35Z)
• Long-form factuality in large language models [60.07181269469043]
  Large language models (LLMs) often generate content that contains factual errors when responding to fact-seeking prompts on open-ended topics. We benchmark a model's long-form factuality in open domains, using GPT-4 to generate LongFact. We then propose that LLM agents can be used as automated evaluators for long-form factuality through a method which we call Search-Augmented Factuality Evaluator (SAFE)
  arXiv  Detail & Related papers  (2024-03-27T17:48:55Z)
• QLoRA: Efficient Finetuning of Quantized LLMs [66.58009990713134]
  We present QLoRA, an efficient finetuning approach that reduces memory usage enough to finetune a 65B parameter model on a single 48GB GPU. QLoRA backpropagates through a frozen, 4-bit quantized pretrained language model into Low Rank Adapters(LoRA) Our best model family, which we name Guanaco, outperforms all previous openly released models on the Vicuna benchmark.
  arXiv  Detail & Related papers  (2023-05-23T17:50:33Z)
• Improving Object Detection, Multi-object Tracking, and Re-Identification for Disaster Response Drones [11.84256047381657]
  We aim to detect and identify multiple objects using multiple cameras and computer vision for disaster response drones. Two simple approaches are proposed to solve these issues. One is a fast multi-camera system that added a tracklet association, and the other is incorporating a high-performance detector and tracker to resolve restrictions.
  arXiv  Detail & Related papers  (2022-01-05T07:56:58Z)

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.