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 Machine Learning
5d ago
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 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 AI
Jul 8
StateFuse: Deterministic Conflict-Preserving Memory for Multi-Agent Systems
arXiv:2607. 05844v1 Announce Type: new Abstract: Agent systems accumulate conflicting observations across branches, retries, and replicas, yet many practical memory layers still collapse disagreement behind overwrite rules that are difficult to inspect or correct.
arXiv Machine Learning
Jul 31
From Expert Reduction to Behavioral Divergence: Tracing Numerical State through Sparse MoE Inference
arXiv:2607. 28097v1 Announce Type: new Abstract: Mathematically equivalent expert-reduction orders can produce observably different sparse-MoE executions.
arXiv AI
Aug 7
Runtime Observability for Heterogeneous Attention Memory
arXiv:2608. 05863v1 Announce Type: new Abstract: Modern models no longer keep a plain KV cache: latent caches, learned sparse selectors and recurrent states each carry the model's memory in a different form, and each fails differently under compression.
arXiv Machine Learning
2d ago
The Integer Alibi: Localizing Cross-Kernel Divergence in INT8-Quantized LLM Inference
arXiv:2608. 13756v1 Announce Type: new Abstract: Two GPU kernels implementing the same scaled INT8 GEMM interface are usually treated as interchangeable.
arXiv AI
Jul 22
Binding Drift in Multi-Step Tool-Augmented Agents
arXiv:2607. 18316v1 Announce Type: cross Abstract: Tool-augmented language-model agents execute multi-step workflows over external systems, resolving an entity once and then acting on it across subsequent steps.
arXiv AI
Aug 12
From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents
arXiv:2608. 10502v1 Announce Type: new Abstract: Persistent memory lets language-model agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed record can alter reasoning, tool use, answers, and subsequent memory writes.
arXiv Machine Learning
Jun 19
Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving
arXiv:2606. 20537v1 Announce Type: new Abstract: Mainstream LLM serving systems reuse prefix work mainly through paged or radix key-value (KV) caches.