arXiv subjects

Kaihua Liang

Publications and source records attributed to Kaihua Liang.

4 recordsLinked to original sources

arXiv2026

Affix Cache for Diffusion Large Language Models

Diffusion Large Language Models (DLLMs) enable non-autoregressive decoding, but efficient inference support remains immature: unlike autoregressive models, whose requests reuse a shared prefix key-value (KV) cache, DLLMs use bidirectional attention, so a shared context's KV states depend on the tokens still being decoded, leaving directly reused caches stale and full recomputation necessary. We present ACache, a cross-request cache reuse mechanism for shared spans, or affixes, at any position: prefix, infix, or suffix. ACache measures the influence of affix tokens on the masked generation region to identify a small request-specific subset as Anchor Tokens, and recomputes only their KV states while reusing the remaining affix cache. Built on state-of-the-art intra-request caching mechanisms, ACache recovers most of the accuracy lost to direct affix-cache reuse on average when recomputing around 20% of affix tokens, and at that budget preserves more accuracy than selection criteria adapted from prior cross-request cache-reuse systems. We co-design ACache with a modern inference engine, whose attention reads each request's recomputed Anchor KV states alongside one affix cache shared across concurrent requests. Against the same system with only intra-request caching, ACache cuts recompute latency by up to 56.7%, translating to as much as 1.71$\times$ end-to-end throughput, while reducing peak KV cache memory by up to 45.8%.

cs.CL↗

arXiv2026

Exploring a Layer-Wise Design Space for KV Cache Eviction

KV cache eviction methods typically use a single retention-rule family throughout a model, making eviction-method identity a model-level design choice. Yet Transformer layers differ substantially in their attention behavior, representations, and sensitivity to compression, suggesting that a uniform rule may overlook useful layer-wise structure. This raises a basic question: should eviction methods themselves vary across layers? We investigate this question by composing existing eviction methods across Transformer layers and systematically exploring the resulting layer-wise design space. Using simple offline profiles, we construct fixed routes and study how their quality varies with method placement and cache budget. On LongBench, heterogeneous routing improves performance on a majority of tasks over homogeneous policies at the same cache budget. Even when method counts are held fixed, the profile-guided placement ranks second among 100 evaluated assignments, demonstrating that routing quality depends strongly on where methods are placed. Moreover, the same fixed route outperforms the best of nine standalone baselines across all five tested cache budgets. Together, these results establish layer-wise method composition as an exploitable, placement-sensitive design dimension for KV cache compression.

cs.LG↗

arXiv2026

EMAS: Stabilizing Multi-Agent System Evolution through Evidence-Guided Revision

Many methods for automated multi-agent system design optimize prompts and topologies during an initial design stage and then deploy the resulting system unchanged on subsequent samples. Experience from these samples is rarely consolidated into reusable system updates, while accuracy-oriented designs may incur high token costs. We introduce EMAS (Evolving Multi-Agent System), which uses this experience to revise MAS topology and prompts without updating LLM parameters, either to improve accuracy or to reduce cost. EMAS converts traces into structured diagnoses that specify a revision operation and target. It generates a candidate revision only when the same diagnosis recurs across samples and applies it only if paired validation against the current MAS meets the corresponding acceptance criterion. Across four benchmarks and two LLMs, EMAS attains the highest task-weighted overall accuracy for both backbones and is best or tied in six of eight model--benchmark settings. Within two evolution epochs, EMAS achieves relative gains of 6.30% and 20.10% in task-weighted accuracy on Kimi-K2-6 and Qwen3.6-27B, respectively. On MBPP with Qwen3.6-27B, EMAS raises accuracy from 55.09% to 89.12% while reducing token use per task by 62.2%. These results show that EMAS can turn experience from new samples into reusable updates to MAS topology and prompts.

cs.AI↗

arXiv2026

FOCUS: DLLMs Know How to Tame Their Compute Bound

Diffusion Large Language Models (DLLMs) offer a compelling alternative to Auto-Regressive models, but their deployment is constrained by high decoding cost. In this work, we identify a key inefficiency in DLLM decoding: while computation is parallelized over token blocks, only a small subset of tokens is decodable at each diffusion step, causing most compute to be wasted on non-decodable tokens. We further observe a strong correlation between attention-derived token importance and token-wise decoding probability. Based on this insight, we propose FOCUS, an inference system designed for DLLMs. By dynamically focusing computation on decodable tokens and evicting non-decodable ones on-the-fly, FOCUS increases the effective batch size, alleviating compute limitations and enabling scalable throughput. Empirical evaluations demonstrate that FOCUS achieves up to 3.52$\times$ throughput improvement over the production-grade engine LMDeploy in large-batch settings, while preserving or improving generation quality across multiple benchmarks.

cs.LG↗