CORTEXA
← Browse
arxivcs.LGcs.AIcs.CL2026-07-23

Error Certificates for KV-Cache Eviction via Randomized Design

Peng Xie

Deterministic KV-cache eviction keeps the top-$k$ tokens under an importance score and deletes the rest. We prove that this design cannot know what it destroyed: evicted values can be altered so that everything the serving system retains is unchanged while the true attention-output error grows arbitrarily, so no serving-time estimator of that error is consistent. Randomized eviction restores identifiability. With a Poisson-sampled tail at known inclusion probabilities, one logit offset performs the Hájek correction inside the softmax, and a survey-sampling variance estimator over the retained set becomes a per-step error certificate with 0.97 empirical coverage at no accuracy cost. On real workloads we pre-registered seven claims and lost three: question-aware eviction at 25--50\% budgets is nearly free; output log-probability predicts failure better than the certificate; certificate-gated budget escalation adds nothing. What survives is attribution: the certificate separates cache-induced from inherent failures (AUC 0.73--0.75, against 0.47--0.54 for output confidence) and schedules recomputation better than random or confidence gating. Randomization buys attribution, not prediction.

View free PDFSource page

Related papers

arxivcs.CLcs.AIcs.LGcs.PF2026-07-15

Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel

Sietse Schelpe

We report a way to make a frozen small language model both more capable and dramatically cheaper at once, without changing any weights. Verified knowledge is deposited once as a byte-exact key-value (KV) state artifact and later restored, by graft, into a fresh inference context.…

View free PDFSource page
arxivcs.LGcs.AIcs.CL2026-07-09Cited by 2

Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization

Jiantong Jiang, Peiyu Yang, Rui Zhang, Feng Liu

Despite the rapid advancements of large language models (LLMs), LLM serving systems remain memory-intensive and costly. The key-value (KV) cache, which stores KV tensors during autoregressive decoding, is crucial for enabling low-latency, high-throughput LLM inference serving. In…

View free PDFSource page
arxivcs.CLcs.AIcs.LG2026-07-14

Adaptive Filtering of the KV Cache: Diagnosing and Correcting Structural-Role Bias in LLM Inference

Soumil Mandal

Attention-based KV cache eviction (H2O and its descendants) compresses the memory-constrained state of a long-context model by ranking tokens on accumulated attention mass, treated here as signal energy, and keeping the heaviest. On schema-dense input streams such as nested JSON,…

View free PDFSource page
arxivcs.LGcs.AIcs.CLcs.OS2026-07-19

WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning

Ryan Xu, Atlas Zhao, David Bao, Frank Du

Long-horizon rollout generation has become the dominant systems bottleneck in agentic reinforcement learning (RL). As agents interact with environments over many turns, trajectories rapidly grow to tens of thousands of tokens, making synchronous RL training increasingly constrain…

View free PDFSource page
arxivcs.CLcs.AIcs.LG2026-07-03

Reading Between the Dots: Decoding Hidden Computation across Filler Tokens

Kaley Brauer, Claudio Mayrink Verdun, Samuel Marks

Frontier LLMs can perform multi-step reasoning over content-free filler tokens like dots or counting sequences, producing correct answers with no visible chain-of-thought (CoT). This is a limit case for behavioral oversight, where surface tokens carry no information about the und…

View free PDFSource page
arxivcs.CLcs.AIcs.LG2026-07-01

Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation

Shayan Talaei, Abhinav Chinta, Devvrit Khatri, Amin Karbasi, Azalia Mirhoseini, Amin Saberi

Language models deployed in high-stakes roles can potentially favor certain entities, brands, or viewpoints, steering user decisions at scale. Such preferential biases can be introduced by any actor in the model's supply chain and are most dangerous when the model reveals its pre…

View free PDFSource page