When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict

• URL: http://arxiv.org/abs/2608.13921v1
• Date: Fri, 14 Aug 2026 03:48:08 GMT
• Title: When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict
• Abstract summary: We introduce underlineTesting underlineAgents' underlineNavigation of underlineGenuine, underlineLatent, and underlineEntangled Memory Conflicts (textscTANGLE)<n>It comprises 541 instances across 40 personas and three types: Context-Partitioned Conflict (CPC), Behavior-Oscillation Conflict (BOC), and Source-Contradiction Conflict ( SCC)<n>We evaluate two tracks---an oracle track with curated memory
• Score: 36.17544860911908
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM agents increasingly maintain personal memory across sessions, but it can conflict. Preferences depend on context, behavior evolves, and sources can conflict. When a query lacks context, time, or source authority to interpret conflict, treating one memory as definitive converts unresolved conflict into an unjustified, overconfident action. Existing benchmarks recover one answer from conflicting evidence, overlooking whether agents recognize underdetermination, preserve alternatives, seek missing information, and choose appropriate actions. We introduce \underline{T}esting \underline{A}gents' \underline{N}avigation of \underline{G}enuine, \underline{L}atent, and \underline{E}ntangled Memory Conflicts (\textsc{TANGLE}), a benchmark for genuinely unresolvable memory conflicts. It comprises 541 instances across 40 personas and three types: Context-Partitioned Conflict (CPC), Behavior-Oscillation Conflict (BOC), and Source-Contradiction Conflict (SCC). We evaluate two tracks---an oracle track with curated memory and a pipeline track that extracts memory from multi-session dialogues---on five dimensions: conflict perception, causal reasoning, confidence calibration, clarification seeking, and memory faithfulness. Experiments reveal pipeline challenges. With curated memory, models recognize conflicts more reliably than they calibrate actions or seek targeted clarification. With end-to-end pipeline memory, extraction fails to preserve conflict-bearing relations needed for downstream reasoning. Policy comparisons show fixed rules are insufficient when actions must reflect conflict. These findings motivate Conflict-Aware Action Policy (CAAP), which adapts actions to each conflict using available evidence. \textsc{TANGLE} frames conflict handling as recognizing underdetermination, retaining conflicting evidence, and acting without forcing a definitive answer.

Related papers

• StateFuse: Deterministic Conflict-Preserving Memory for Multi-Agent Systems [6.160059055899747]
  StateFuse is a conflict-aware replicated memory contract built on standard OpSet/CRDT merge.<n>We evaluate StateFuse against flat multi-value, raw-log, provenance-style, and collapsed baselines under matched resolver and verification policies.
  arXiv  Detail & Related papers  (2026-07-07T05:06:33Z)
• ConflictScore: Identifying and Measuring How Language Models Handle Conflicting Evidence [48.938290419832335]
  We introduce ConflictScore, a novel metric that quantifies how well a model's response acknowledges conflicting evidence in its grounding documents.<n>Our framework decomposes responses into atomic claims, labels each claim against each grounding document, and then aggregates these labels into two complementary measures: ConflictScore-Count (CS-C), the proportion of claims exhibiting conflicts, and ConflictScore-Ratio (CS-R), the balance between supporting and contradicting evidence.
  arXiv  Detail & Related papers  (2026-06-24T23:00:09Z)
• MemConflict: Evaluating Long-Term Memory Systems Under Memory Conflicts [19.9199366981741]
  We propose a diagnostic framework that treats memory validity as a query-conditioned fitness-for-use problem.<n>MemConflict formalizes dynamic, static, and conditional conflicts over temporal validity, factual correctness, and contextual applicability.<n>It simulates controlled long-horizon histories from structured user profiles, introduces cross-session conflicts, and injects semantically similar distractors to create competition among memory candidates.
  arXiv  Detail & Related papers  (2026-05-20T09:11:04Z)
• Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding [51.242997961841276]
  Large language models accumulate parametric knowledge through pre-training.<n> knowledge conflicts occur when outdated or incorrect parametric knowledge conflicts with external knowledge in the context.<n>Existing methods address knowledge conflicts through contrastive decoding, but in conflict-free scenarios, static approaches disrupt output distribution.<n>We propose Dynamic Cognitive Reconciliation Decoding (DCRD), to predict and context-memory conflicts.
  arXiv  Detail & Related papers  (2026-05-12T14:29:45Z)
• To Fuse or to Drop? Dual-Path Learning for Resolving Modality Conflicts in Multimodal Emotion Recognition [87.22988227382329]
  Multimodal emotion recognition (MER) benefits from combining text, audio, and vision, yet standard fusion often fails when modalities conflict.<n>We propose Dual-Path Conflict Resolution (DCR), a unified framework that learns when to fuse and when to drop modalities.
  arXiv  Detail & Related papers  (2026-05-06T13:11:33Z)
• Conflicts Make Large Reasoning Models Vulnerable to Attacks [17.460309581795595]
  This work investigates how LRMs respond to harmful queries when confronted with two categories of conflicts.<n>Internal conflicts pit alignment values against each other and dilemmas impose mutually contradictory choices.<n>Using over 1,300 prompts across five benchmarks, we evaluate three representative LRMs.
  arXiv  Detail & Related papers  (2026-04-10T11:44:57Z)
• Rashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memory [0.0]
  Rashomon Memory is an architecture where parallel goal-conditioned agents encode experiences according to their priorities and negotiate at query time through argumentation.<n>We show that retrieval modes emerge from attack graph topology, and that the conflict surfacing mode, where the system reports genuine disagreement rather than forcing resolution, lets decision-makers see the underlying interpretive conflict directly.
  arXiv  Detail & Related papers  (2026-04-04T04:29:50Z)
• Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning [78.86309644343295]
  Multimodal large language models (MLLMs) in long chain-of-thought reasoning often fail when different knowledge sources provide conflicting signals.<n>We formalize these failures under a unified notion of knowledge conflict, distinguishing input-level objective conflict from process-level effective conflict.<n>Our findings provide a mechanism-level view of multimodal reasoning under knowledge conflict and enable principled diagnosis and control of long-CoT failures.
  arXiv  Detail & Related papers  (2026-02-16T07:10:44Z)
• AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge [57.66282463340297]
  Knowledge conflict arises from discrepancies between information in the context of a large language model and the knowledge stored in its parameters.<n>We propose a fine-grained, instance-level approach called AdaCAD, which dynamically infers the weight of adjustment based on the degree of conflict.<n>We show that ADACAD consistently outperforms other decoding baselines with average QA accuracy gains of 14.21% (absolute) over a static contrastive baseline, and improves the factuality of summaries by 6.19 (AlignScore)
  arXiv  Detail & Related papers  (2024-09-11T16:35:18Z)

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.