arXiv Machine Learning
Jul 31
Subtract or Replay? Exact Deletion from Language-Model Memory
arXiv:2607. 27539v1 Announce Type: new Abstract: Exact deletion from persistent language-model memory depends on how that memory represents a record.
Stage-Replay Divergence Follows the KV Cache: Fixed-Prefix Precision Controls and Bidirectional Cache Transplantation
arXiv:2607. 28495v1 Announce Type: new Abstract: Stage-replay diagnostics reconstruct intermediate token prefixes and treat fresh-prefill continuation as continuation from the decoder state that originally reached the prefix.
Related stories
arXiv AI
Jul 17
Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel
arXiv:2607. 14431v1 Announce Type: cross Abstract: We report a way to make a frozen small language model both more capable and dramatically cheaper at once, without changing any weights.
arXiv Computation and Language
Aug 28
SCIT: Testing Causal Cache Carriers in Latent Chain-of-Thought Models
SCIT (Suffix Cache Interchange Test) is a causal protocol designed to identify which transformer components carry counterfactual computations in latent chain-of-thought models. By constructing exact source‑recipient counterfactuals and applying sufficiency tests, K/V splits, hidden‑state controls, and semantic source controls, SCIT demonstrates that counterfactual arithmetic primarily transfers through value‑cache suffix trajectories rather than hidden states or keys. The method reveals carrier‑regime shifts across different GPT‑2 checkpoints, providing a cache‑level diagnostic and a competence‑gated carrier map for arithmetic mechanisms.
arXiv AI
Sep 15
Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCache
arXiv:2609.15030v1 Announce Type: cross Abstract: External cache transfers can succeed while a hybrid language model resumes from an inconsistent state. We examine the full 45-layer GLM-5.3-Flash mod...
arXiv Machine Learning
Sep 10
Exact Record Omission in Delta Attention: A Transport Criterion, Its Cost, and a Replay Certificate
arXiv:2609.06872v1 Announce Type: new Abstract: When a user asks an assistant to forget a record, the test is whether the memory now matches the state it would hold if the record had never been store...
arXiv Machine Learning
Aug 14
Subtract, Transport, or Replay? Auditable Deletion from Language-Model Memory
arXiv:2607. 27539v2 Announce Type: replace Abstract: Exact deletion from persistent language-model memory depends on whether a record's effect remains addressable after later computation.
arXiv AI
Sep 7
Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents
arXiv:2609. 04875v1 Announce Type: cross Abstract: Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache.
arXiv AI
Sep 2
Invalidation Contracts for Cross-Episode Agent Memory
The paper proposes invalidation contracts to manage cached recovery suggestions in LLM agents, attaching version stamps and cacheability hints to each suggestion so stale entries can be evicted without trial and error. The protocol separates realized savings into validity (protocol‑dependent) and compliance (planner‑dependent), showing that row‑level invalidation can significantly improve first‑try compliance and recover a substantial portion of token costs across multiple models, while table‑level invalidation can be detrimental. The study evaluates the approach across seven models, three serving paths, two domains, and about 9,400 episodes, demonstrating deterministic validity and high eviction precision.
arXiv Machine Learning
Jun 16
Re-feeding Is Not Replaying: Measuring Replay Noise in Counterfactual Token-Credit Estimation
arXiv:2606. 15621v1 Announce Type: new Abstract: Per-token counterfactual credit estimation asks which token in a language-model rollout caused the final answer to be right or wrong: cut the transcript at a pivot, substitute an alternative token, replay continuations, and compare outcomes.
arXiv Machine Learning
Aug 11
The Replay Gap: Static Evaluation of Model Switching in LLM Agents Scores the Wrong World
arXiv:2608. 08239v1 Announce Type: new Abstract: LLM routers promise efficiency by matching each request to the cheapest adequate model, and are increasingly applied per step inside multi-step agents.
arXiv Machine Learning
5d ago
CacheReforge: Bounded Recovery for Stale KV Caches under Evolving Adapters
CacheReforge is a method for recovering stale key‑value (KV) caches in large language models when lightweight adapters evolve. It represents stale caches as layer‑wise mixed‑version objects and uses adapter anchors, sensitivity calibration, drift accumulation, and restart boundaries to decide between direct reuse, bounded recomputation, or full suffix recovery. Experiments on Qwen2.5 models with continual LoRA updates show a 92.4% reduction in mean KL divergence while only recomputing 5.44% of layers and cutting cache‑maintenance time by 93.2% compared to full prefill.
arXiv Machine Learning
Sep 23
PatchKV: Efficient KV Cache Recovery for Dynamically Edited LLM Contexts
arXiv:2609.26219v1 Announce Type: cross Abstract: Long-running LLM agent workflows often revise interior context spans while retaining long suffixes. Although suffix tokens remain unchanged, altered...