When Does Trace-Driven Evaluation Mislead MoE Expert Caching? Replay Semantics, Workload Contamination, and Operating Regimes

• URL: http://arxiv.org/abs/2608.07911v2
• Date: Thu, 13 Aug 2026 06:19:20 GMT
• Title: When Does Trace-Driven Evaluation Mislead MoE Expert Caching? Replay Semantics, Workload Contamination, and Operating Regimes
• Abstract summary: Mixture-of-Experts (MoE) models have outgrown accelerator memory.<n>Policy that raised the hit rate would cut expert traffic per token.<n>We evaluate three evaluation axes that change conclusions, not just numbers.
• Score: 3.471896896439183
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mixture-of-Experts (MoE) models have outgrown accelerator memory, and offloading expert weights to host memory is now standard. This makes expert cache management an attractive lever: a policy that raised the hit rate would cut expert traffic per token. Evaluating that is a measurement problem, and we find the measurement fragile. With a trace-driven, event-atomic simulator over three MoE models (40, 64, 128 experts), we isolate three evaluation axes that change conclusions, not just numbers. Replay semantics: under a fused-event traffic contract, an inconsistent per-access replay inflates recency-based policies by 27-29% while leaving frequency-based and static ones within 4%, inverting the policy ranking. Workload contamination: probe sets using one instruction template per category produce verbatim-identical generation prefixes; a matched-pair rendering intervention moves the measured early-window effect by 19.4-31.9 points and reverses which workloads look most cache-friendly. Operating regimes: normalized miss fractions do not transfer across models, so the per-step expert union relative to per-layer capacity must be reported -- yet permuting only the temporal order of an identical event stream moves the offline-optimal gap from 44.9% to 30.8%, so it is not sufficient. Corrected, a stable gap to the offline optimum remains (44.2-45.9% over 13 frozen workload compositions). A forced-admission oracle attributes 84.3-96.6% of it to knowing which resident expert is used furthest in the future. A causal next-use predictor, used as an eviction rule, recovers -11.4% of the gap; it picks an optimal victim 3.4% of the time, against 2.4% for a random resident block and 20.6-22.1% for LRU and LFRU. Our position is narrow: in our evaluated settings a large offline-optimal gap substantially overstates the gains recovered by representative lightweight causal mechanisms.

Related papers

• CAPTURE: Disentangling Preference Drift from Memory Poisoning in Personalized LLM Agents [0.15293427903448023]
  CAPTURE is a continuous-time partially observable decision process over a latent user state.<n>It achieves a 71.5% win rate, compared with 69.3% for an identically supervised baseline.<n>It limits fixed-policy poisoning success to 11.5% while accepting 83.5% of genuine preference updates.
  arXiv  Detail & Related papers  (2026-09-02T08:10:26Z)
• 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)
• Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training [0.0]
  We study SkewAdam, an estimator built on the observation that the three parameter populations of an MoE differ enough in size and gradient statistics that they should not receive the same state.<n>SkewAdam reaches perplexity 108.4, ahead of AdamW (126.8), Muon (120.2), and Lion (393.7), and router load balance settles to within 1% of its uniform floor.
  arXiv  Detail & Related papers  (2026-07-21T12:47:15Z)
• Speculate with Memory: Lossless Acceleration for LLM Agents [41.48103818220709]
  Speculative execution accelerates LLM agents by using a smaller, cheaper model to predict and pre-launch the next step while the environment is idle.<n>We equip the speculator with three online memory systems that learn from past agent trajectories.<n>We evaluate this approach on six benchmarks spanning three speculation types: action prediction, observation prediction, and chained prediction.
  arXiv  Detail & Related papers  (2026-07-14T00:36:31Z)
• Strained Coherence: A Pre-Failure Signal in Coding Agent Execution Trajectories [0.0]
  LLM-based coding agents sometimes acknowledge a problem in their own reasoning and then proceed anyway.<n>We build a Claude Sonnet 4.6 judge that reads full trajectories and flags spans where the pattern occurs.<n>We evaluate it on 44 Terminal-bench-2 trajectories using a Qwen3.5-35B-A3B backbone.
  arXiv  Detail & Related papers  (2026-06-05T22:52:16Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models [60.14219417402433]
  Existing memory benchmarks for LLM agents evaluate explicit recall of facts, yet overlook implicit memory where experience becomes automated behavior without conscious retrieval.<n>We introduce ImplicitMemBench, the first systematic benchmark evaluating implicit memory through three constructs drawn from standard cognitive-science accounts of non-declarative memory.<n>Our 300-item suite employs a unified Learning/Priming-Interfere-Test protocol with first-attempt scoring.
  arXiv  Detail & Related papers  (2026-04-09T10:26:32Z)
• Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode [9.116800340266066]
  Claude Code's auto mode is the first deployed permission system for AI coding agents.<n>Anthropic reports a 0.4% false positive rate and 17% false negative rate on production traffic.<n>We evaluate 253 state-changing actions at the individual action level against oracle ground truth.
  arXiv  Detail & Related papers  (2026-04-04T17:56:30Z)
• Scalable Multi-Task Low-Rank Model Adaptation [43.22544779625565]
  Scaling multi-task low-rank adaptation (LoRA) to a large number of tasks induces catastrophic performance degradation.<n>We find that existing solutions, like regularization and dynamic routing, fail at scale because they are constrained by a fundamental trade-off.<n>We propose mtLoRA, a scalable solution with three novel designs.
  arXiv  Detail & Related papers  (2026-03-02T06:57:11Z)
• Echoes of Human Malice in Agents: Benchmarking LLMs for Multi-Turn Online Harassment Attacks [10.7231991032233]
  Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm.<n>We present the Online Harassment Agentic Benchmark consisting of: (i) a synthetic multi-turn harassment conversation dataset, (ii) a multi-agent (e.g., harasser, victim) simulation informed by repeated game theory, (iii) three jailbreak methods attacking agents across memory, planning, and fine-tuning, and (iv) a mixed-methods evaluation framework.
  arXiv  Detail & Related papers  (2025-10-16T01:27:44Z)
• vCache: Verified Semantic Prompt Caching [95.16654660556975]
  This paper proposes vCache, the first verified semantic cache with user-defined error rate guarantees.<n>It employs an online learning algorithm to estimate an optimal threshold for each cached prompt, enabling reliable cache responses without additional training.<n>Our experiments show that vCache consistently meets the specified error bounds while outperforming state-of-the-art static-threshold and fine-tuned embedding baselines.
  arXiv  Detail & Related papers  (2025-02-06T04:16:20Z)
• G$^2$uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering [116.4277292854053]
  Federated Learning (FL) offers collaborative model training without data sharing. FL is vulnerable to backdoor attacks, where poisoned model weights lead to compromised system integrity. We present G$2$uardFL, a protective framework that reinterprets the identification of malicious clients as an attributed graph clustering problem.
  arXiv  Detail & Related papers  (2023-06-08T07:15:04Z)

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.