LLM Inference Efficiency

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

47 papers in the last four weeks, up 262% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 234

May 8, 2026cs.DC

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation

Selecting the optimal LLM inference configuration requires evaluation across hardware, serving engines, attention backends, and model architectures, since no single choice performs best across all workloads. Profile-based simulators are the standard tool, yet they hardcode their operation set to a specific configuration and re-profile every operation from scratch, making exploration prohibitively expensive. This cost stems from a missing structural understanding: every input dimension of each operation is fixed by the model configuration or determined by the incoming request. Many model-configuration values (e.g., head size, layer count) recur across models, so the same operation runs in many configurations; a single sweep over the request-dependent dimensions can serve them all. We present Dooly, which exploits this structure to achieve configuration-agnostic, redundancy-aware profiling. Dooly performs a single inference pass, labels each input dimension with its origin via taint propagation, and selectively profiles only operations absent from its latency database; stateful operations such as attention are isolated by reusing the serving engine's own initialization code, eliminating manual instrumentation. It builds latency regression models based on the database, which becomes a drop-in backend for existing simulators. Across two GPU platforms, three attention backends, and diverse model architectures, Dooly achieves simulation accuracy within 5% MAPE for TTFT and 8% for TPOT while reducing profiling GPU-hours by 56.4% across 12 models compared to the existing profiling approach. We have open-sourced Dooly at https://github.com/dooly-project.

Joon Ha Kim, Geon-Woo Kim, Anoop Rachakonda +1

University of Texas at Austin

LLM Inference Efficiency LLM Inference

May 8, 2026cs.CL

Learning Agent Routing From Early Experience

LLM agents achieve strong performance on complex reasoning tasks but incur high latency and compute cost. In practice, many queries fall within the capability boundary of cutting-edge LLMs and do not require full agent execution, making effective routing between LLMs and agents a key challenge. We study the problem of routing queries between lightweight LLM inference and full agent execution under realistic cold-start settings. To address this, we propose BoundaryRouter, a training-free routing framework that uses early behavioral experience and rubric-guided reasoning to decide whether to answer a query with direct LLM inference or escalate to an agent. BoundaryRouter builds a compact experience memory by executing both systems on a shared seed set and retrieves similar cases at inference time to guide routing decisions. To evaluate this method, we introduce RouteBench, a benchmark covering in-domain, paraphrased, and out-of-domain route settings. Experiments show that BoundaryRouter reduces inference time by 60.6% compared to the agent while improving performance by 28.6% over direct LLM inference, outperforming prompt-based and retrieval-only routing by an average of 37.9% and 8.2%, respectively.

Yimin Wang, Jiahao Qiu, Xuan Qi +6

University of Michigan · Shanghai Jiao Tong University · AI Lab, Princeton University +3

LLM Inference Efficiency LLM Agent Routing

May 7, 2026cs.LG

Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management

LLM-based workflows compose specialized agents to execute complex tasks, and these agents usually share substantial context, allowing KV-Cache reuse to save computation. Existing approaches either manage KV-Cache at agent level and fail to exploit the reuse opportunities within workflows, or manage cache at the workflow level but assume that each workflow calls a static sequence of agents. However, practical workflows are typically dynamic, where the sequence of invoked agents and thus induced cache reuse opportunities depend on the context of each task. To serve such dynamic workflows efficiently, we build a system dubbed PBKV (\textbf{P}rediction-\textbf{B}ased \textbf{KV}-Cache Management). For each workflow, PBKV predicts the agent invocations in several future steps by fusing the guidance from historical workflows and context of the target workflow. Based on the predictions, PBKV estimates the reuse potential of cache entries and keeps the high-potential entries in GPU memory. To be robust to prediction errors, PBKV utilizes the predictions conservatively during both cache eviction and prefetching. Experiments on three workflow benchmarks show that PBKV achieves up to

1.85\times

speedup over LRU on dynamic workflows, and up to

1.26\times

speedup over the SOTA baseline KVFlow on the static workflow.

Haoyu Zheng, Fangcheng Fu, Jia Wu +6

Wuhan University · Shanghai Jiao Tong University · Macquarie University +2

LLM Inference Efficiency KV Caching Agentic Workflows KV-Cache Management LLM Agent Workflow Optimization KV-Cache Reuse

May 7, 2026cs.LG

Towards Generation-Efficient Uncertainty Estimation in Large Language Models

Uncertainty estimation is important for deploying LLMs in high-stakes applications such as healthcare and finance, where hallucinations can appear fluent and plausible while being factually incorrect, making it difficult for users to judge whether an output should be trusted. Existing methods require one or more full autoregressive generations to estimate uncertainty, which introduces substantial inference cost and often delays uncertainty assessment. In this paper, we investigate whether effective uncertainty estimation can be achieved with partial generation or even input-only information. Specifically, we first develop a unified framework that formulates uncertainty estimation as an early estimation problem over the autoregressive generation process of LLMs. This framework organises existing and proposed estimators by the information they observe, ranging from multi-generation to input-only prediction, and clarifies the performance-cost trade-off underlying different uncertainty estimation methods. Building on this view, we study two largely underexplored low-cost settings: estimating uncertainty with part of the generation, and predicting uncertainty from the input prompt. We propose Logit Magnitude, which uses top-M logit evidence to estimate uncertainty from an early-stopped generation prefix, and MetaUE, which distils generation-based uncertainty into a lightweight input-only estimator trained with uncertainty scores. Extensive experiments on general and domain-specific benchmarks show that Logit Magnitude achieves strong performance, and partial generations of LLMs are often sufficient for effective uncertainty estimation. MetaUE further provides a competitive input-only approximation in several settings. These findings suggest that effective uncertainty estimation requires less generation than commonly assumed, enabling unreliable responses to be identified earlier.

Mingcheng Zhu, Yu Liu, Tingting Zhu

University of Oxford

LLM Inference Efficiency Uncertainty Quantification Confidence Estimation in Language Models LLM Reliability LLM Uncertainty Estimation

May 6, 2026cs.DC

One Pool, Two Caches: Adaptive HBM Partitioning for Accelerating Generative Recommender Serving

Generative Recommender (GR) inference places embedding hot caches (EMB) and KV caches in direct competition for limited GPU HBM: allocating more memory to one improves its efficiency but degrades the other. Existing systems optimize them in isolation, overlooking that the optimal EMB-KV allocation ratio can shift by up to 0.35 across workload regimes, leaving 20-30% latency improvement unrealized. While online reallocation is required to close this gap, naive approaches introduce H2D refill traffic on the critical path, causing P99 SLO violations. To address this, we present HELM, which jointly manages HBM allocation and request routing at runtime through two key components: (1) Adaptive Memory Allocation, a three-layer PPO-based controller (frozen base policy, online residual adapter, and burst-aware recovery controller) that achieves

32\,\mathrm{μs}

decision latency while staying within 0.024-0.029 of the offline-optimal ratio; and (2) EMB-KV-Aware Scheduling, which routes requests by jointly considering KV residency, embedding locality, and node load to avoid routing inefficiencies under heterogeneous allocations. Evaluations on three production-scale datasets over a 32-node A100 cluster show that HELM reduces P99 latency by 24-38% over the best static policy and achieves 93.5-99.6% SLO satisfaction across Steady, Trend, and Burst workloads, significantly outperforming state-of-the-art baselines without sacrificing throughput.

Wenjun Yu, Shuguang Han, Amelie Chi Zhou

Hong Kong Baptist University · Hong Kong, China · Alibaba Inc +1

LLM Inference Efficiency GPU Acceleration KV Caching Online Resource Allocation Generative Recommendation

May 5, 2026cs.LG

Adaptive Consensus in LLM Ensembles via Sequential Evidence Accumulation: Automatic Budget Identification and Calibrated Commit Signals

Large Language Model ensembles improve reasoning accuracy, but only up to a performance boundary beyond which additional deliberation degrades accuracy. We introduce DASE (Deliberative Adaptive Stopping Ensemble), a stopping heuristic for iterative ensemble deliberation that commits early on genuine consensus and applies a global-frequency fallback on fragmented evidence. We make three contributions. (1) DASE produces a commit-type routing partition that generalises across benchmarks and is complementary to verbalized single-call confidence. On GPQA-Extended (N=546, 70B ensemble), the partition yields a 39.5 pp routing gap (right-wall 81.1% vs. left-wall 41.5%). On AIME 2010-2023 (N=261, 120B ensemble, 3 seeds), right-wall commits reach 98.3% accuracy vs. left-wall 72.8% (25.5 pp gap), statistically equivalent to Opus 4.6 Standard verbalized confidence at matched coverage (25.7 pp gap; bootstrap p=0.873); the two mechanisms disagree on 37% of routing assignments. (2) Adaptive stopping, not injection bandwidth, drives accuracy. On AIME-300, bandwidth accounts for only 0.3 pp (ns). On GPQA-Extended at the 120B tier, sparse injection (

\approx15

tokens/worker/round) achieves 70.9% with a 30.7 pp routing gap; dense injection (

\approx600

chars/worker/round) achieves 72.2% but with halved right-wall coverage and a narrower 18.9 pp gap. (3) Injection-based methods exhibit an inverted-U accuracy-vs-inference trajectory; this pattern is hypothesis-generating.

Roberto E. Medina

Independent Researcher

LLM Inference Efficiency Multi-Agent Consensus LLM Routing Language Model Ensembles

May 5, 2026cs.DC

Tile-Level Activation Overlap for Efficient LLM Inference

SwiGLU is the dominant MLP activation in modern large language models, yet its intermediate tensor materialization costs 9-37% of MLP execution time. We present two complementary CUTLASS-based SM90 kernels that fuse SwiGLU into GeMM at the tile level. Kernel-1 overlaps Swish computation on the Gate accumulator with Up-tile loading using the Pingpong warp-specialized schedule; Kernel-2 interleaves SwiGLU with tile stores via a custom Epilogue Visitor Tree. Evaluated on Qwen-2.5 models (0.5B-72B) on NVIDIA H100, our kernels achieve up to 2.47x speedup over PyTorch, shifting workloads from memory-bound to compute-bound and reaching 79.5% peak BF16 utilization. We demonstrate that torch.compile cannot replicate this fusion (3-7x slower than our kernels), validating the need for hand-crafted tile-level design. Our fused kernels are also numerically superior, achieving zero mismatches compared to 4.5-11% for cuBLAS.

Abhinav Jangda, Tyler Sorensen, Sebastian Burckhardt +3

Microsoft Research · Microsoft

LLM Inference Efficiency GPU Kernel Optimization GPU Acceleration LLM Inference High-Performance Computing

May 3, 2026cs.NI

Human-Less LLM Serving: Quantifying the Human Tax on Throughput

Every major LLM serving system is designed to meet TTFT and TPOT SLOs. These metrics capture latency as a human user perceives it, and the mechanisms built to satisfy them are now standard infrastructure. We observe that long-horizon AI tasks call LLMs programmatically in tight loops where no human observes TTFT or TPOT. We ask: how much throughput do serving systems sacrifice to meet TTFT and TPOT SLAs that these workloads never need? We conduct a systematic measurement study across chunk sizes, SLO settings, context lengths, and concurrency levels. We find that the human tax on throughput grows substantially with context length and lands in the 60-93% range. At 64K token contexts, tightening the TTFT SLO to production-typical settings costs a large fraction of throughput versus the human-less baseline. The human tax is larger at higher concurrency and is qualitatively similar across SGLang and Sarathi-Serve. We term the unconstrained optimum human-less serving and provide a prototype demonstrating that it is practical on real workloads. Our findings argue that serving systems should expose workload-class-aware SLA configurations rather than silently applying the human tax uniformly to all traffic.

Jianhui Lian, Li Chen, Dan Li +1

Tsinghua SIGS · Beijing Zhongguancun Laboratory · Tsinghua University

LLM Inference Efficiency LLM Serving

May 1, 2026cs.LG

AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices

Autonomous agents powered by large language models (LLMs) are increasingly used to automate complex, multi-step tasks such as coding or web-based question answering. While remote, cloud-based agents offer scalability and ease of deployment, they raise privacy concerns, depend on network connectivity, and incur recurring API costs. Deploying agents locally on user devices mitigates these issues by preserving data privacy and eliminating usage-based fees. However, agentic workflows are far more resource-intensive than typical LLM interactions. Iterative reasoning, tool use, and failure retries substantially increase token consumption, often expending significant compute without successfully completing tasks. In this work, we investigate the time, token, and energy overhead of locally deployed LLM-based agents on consumer hardware. Our measurements show that agentic execution increases GPU power draw, temperature, and battery drain compared to single-inference workloads. To address this inefficiency, we introduce AgentStop, a lightweight efficiency supervisor that predicts and preemptively terminates trajectories unlikely to succeed. Leveraging low-cost execution signals, such as token-level log probabilities, AgentStop can reduce wasted energy by 15-20% with minimal impact on task performance (<5% utility drop) for challenging web-based question answering and coding benchmarks. These findings position predictive early termination as a practical mechanism for enabling sustainable, privacy-preserving LLM agents on user devices. Our project code and data are available at https://github.com/brave-experiments/AgentStop.

Dzung Pham, Kleomenis Katevas, Ali Shahin Shamsabadi +1

University of Massachusetts Amherst Amherst, Massachusetts, USA · Brave Software London, UK · Brave Software, Imperial College London London, UK

LLM Inference Efficiency On-Device Language Model Inference LLM Agents

May 1, 2026cs.DC

SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters

AI agents execute tens to hundreds of chained LLM calls per task, yet GPU schedulers treat each call as independent, discarding gigabytes of intermediate state between steps and inflating end-to-end latency by 3-8x. We argue that this request-level abstraction is fundamentally mismatched to compound AI workloads, and propose a shift to program-level scheduling: treating the entire agent workflow (not individual inference calls) as the first-class schedulable unit. We present SAGA, a distributed scheduler that implements this abstraction through three mechanisms: (1) Agent Execution Graphs that capture workflow structure to predict KV cache reuse across tool-call boundaries, achieving within 1.31x of Bélády's optimal offline policy; (2) session-affinity batching with work stealing that co-locates correlated requests while maintaining global load balance; and (3) Agent Fair Share, a task-completion-time fairness metric with provable bounded-deviation guarantees. On a 64-GPU cluster serving SWE-bench coding agents and WebArena browser tasks, SAGA reduces task completion time by 1.64x (geometric mean, p < 0.001) over vLLM v0.15.1 with prefix caching and affinity routing, while improving GPU memory utilization by 1.22x and achieving 99.2% SLO attainment under multi-tenant interference. These latency gains come at a quantified cost: approximately 30% lower peak throughput than throughput-optimal batch scheduling, a tradeoff appropriate for the latency-sensitive interactive deployments that dominate compound AI usage. Our results demonstrate that workflow-aware scheduling is essential for efficient compound AI serving.

Dongxin Guo, Jikun Wu, Siu Ming Yiu

LLM Inference Efficiency LLM Agent Orchestration LLM Inference Scheduling

May 1, 2026cs.PF

Silicon Showdown: Performance, Efficiency, and Ecosystem Barriers in Consumer-Grade LLM Inference

The operational landscape of local Large Language Model (LLM) inference has shifted from lightweight models to datacenter-class weights exceeding 70B parameters, creating profound systems challenges for consumer hardware. This paper presents a systematic empirical analysis of the Nvidia and Apple Silicon ecosystems, specifically characterizing the distinct intra-architecture trade-offs required to deploy these massive models. On the Nvidia Blackwell architecture, we identify a critical "Backend Dichotomy" within the TensorRT-LLM stack: while the new NVFP4 quantization format delivers a 1.6x throughput advantage over optimized BF16 baselines (151 tokens/s vs. 92 tokens/s), realizing this performance requires navigating complex runtime constraints that trade startup latency for generation speed. Furthermore, we characterize the "VRAM Wall" for 70B+ models: on discrete GPUs, users face a destructive choice between aggressive quantization (e.g., Q2) that degrades model intelligence to fit in VRAM, or PCIe-bottlenecked CPU offloading, which reduces throughput by over 90% compared to full-GPU execution. Conversely, Apple's Unified Memory Architecture (UMA) circumvents these bottlenecks, enabling linear scaling for 80B parameter models at practical 4-bit precisions. This architectural divergence extends to operational sustainability, where Apple's SoC design demonstrates up to a 23x advantage in energy efficiency (tokens/joule). We conclude that for consumer-grade inference, the optimal hardware is defined by a complex interplay between compute density (Nvidia) and memory capacity (Apple), moderated by the significant "ecosystem friction" of proprietary quantization workflows.

Abdurrahman Javat, Allan Kazakov

Bahcesehir University, Istanbul, Türkiye

LLM Inference Efficiency LLM Quantization On-Device Language Model Inference Energy-Efficient ML

May 1, 2026cs.CL

Agent Capsules: Quality-Gated Granularity Control for Multi-Agent LLM Pipelines

A multi-agent pipeline with N agents typically issues N LLM calls per run. Merging agents into fewer calls (compound execution) promises token savings, but naively merged calls silently degrade quality through tool loss and prompt compression. We present Agent Capsules, an adaptive execution runtime that treats multi-agent pipeline execution as an optimization problem with empirical quality constraints. The runtime instruments coordination overhead per group, scores composition opportunity, selects among three compound execution strategies, and gates every mode switch on rolling-mean output quality. A controlled negative result confirms that injecting more context into a merged call worsens compression rather than relieving it, so the framework's escalation ladder (standard, then two-phase, then sequential) recovers quality by moving toward per-agent dispatch rather than by rewriting merged prompts. On LLM-judged quality, the controller matches a hand-tuned oracle on every measured (model, group, mode) cell: routing compound whenever the oracle would, and reverting to fine whenever quality would fail the floor, without per-model configuration. Against a hand-crafted LangGraph implementation of a 14-agent competitive intelligence pipeline, Agent Capsules uses 51% fewer fine-mode input tokens and 42% fewer compound-mode input tokens, at +0.020 and +0.017 quality respectively. Against a DSPy implementation of a 5-agent due diligence pipeline, the framework uses 19% fewer tokens than uncompiled DSPy at quality parity, and 68% fewer tokens than MIPROv2 at +0.052 quality. Even before compound mode fires, the runtime delivers efficiency through automatic policy resolution, cache-aligned prompts, and topology-aware context injection, matching both hand-tuned and compile-time baselines without training data or per-pipeline engineering.

Aninda Ray

LLM Inference Efficiency Multi-Agent LLM Systems Multi-Agent System Optimization LLM Agent Orchestration LLM Agent Workflow Optimization

May 1, 2026cs.CL

Context Recycling for Long-Horizon LLM Inference

Large language models (LLMs) exhibit strong capabilities in short-context reasoning but degrade in performance over long conversational horizons due to context window limitations and inefficient token usage. We introduce ContextForge, a system for context recycling that maintains task-relevant information across turns by combining structured query generation, external memory retrieval, and controlled synthesis. The system enables efficient reuse of prior computation without relying on full context replay, reducing token overhead while preserving answer quality. We evaluate ContextForge using a 15-turn conversational benchmark that tests multi-turn reasoning, back-references, and domain shifts across structured healthcare queries. Compared to a baseline agent using identical underlying models, ContextForge demonstrates improved consistency and reduced token consumption, while maintaining comparable response accuracy. These results suggest that context recycling provides a practical approach for extending LLM capabilities in long-horizon tasks without requiring larger context windows or model retraining. Code and evaluation artifacts are available at https://github.com/Betanu701/ContextForge.

Derek Thomas

Independent Researcher · contextforge

LLM Inference Efficiency Long-Context Language Model Inference LLM Context Management Memory-Augmented Language Model Agents

Apr 29, 2026cs.SE

LLM-Guided Runtime Parameter Optimization for Energy-Efficient Model Inference

Large Language Models (LLMs) have become an integral part of many real-world workflows. However, LLMs consume a lot of energy, which becomes a large concern in the scale of the demand for these tools. As LLMs become integrated into different workflows, different applications have arisen to deal with the challenge of running inference for these tools. This raises another issue of choosing the runtime parameter values for these services in order to minimize the energy consumption. Oftentimes this requires deep knowledge of the application or traditional optimization methods that can take days to find optimal values. In this work, we created a human-in-the-loop flow with LLM-assisted runtime parameter optimization in order to solve this issue. With human-created, specific feedback prompting methods, chat-based LLMs can iteratively find energy-efficient inference parameters faster than traditional search methods. LLMs can also tailor their solutions to different hardware setups and easily take into account other system constraints. The enhanced prompt template was able to converge below the threshold at an average of 3.4 prompts compared to the baseline, which converged in an average of 5.2 prompts, and consistently achieved lower final energy per token. The enhanced prompt template also outperformed Sobol sampling in convergence speed.

Katelyn Crumpacker, Dimitrios Nikolopoulos

Virginia Polytechnic and State University

LLM Inference Efficiency Energy-Efficient ML Inference-Time Optimization Large Language Model-Guided Optimization

Apr 28, 2026cs.DB

Evergreen: Efficient Claim Verification for Semantic Aggregates

With recent semantic query processing engines, semantic aggregation has become a primitive operator, enabling the reduction of a relation into a natural language aggregate using an LLM. However, the resulting semantic aggregate may contain claims that are not grounded in the underlying relation. Verifying such claims is challenging: they often involve quantifiers, groupings, and comparisons over relations that far exceed LLM context windows and require a costly combination of semantic and symbolic processing. We present Evergreen, a system that recasts claim verification as a semantic query processing task with tailored optimizations and provenance capture. Evergreen compiles each claim into a declarative semantic verification query that can execute on the same query engine used to produce the aggregate. To reduce cost, Evergreen avoids unnecessary LLM calls through verification-aware optimizations, including early stopping, relevance sorting, and estimation with confidence sequences, as well as general-purpose optimizations for semantic queries, such as operator fusion, similarity filtering, and prompt caching. Each verdict is accompanied by citations that identify a minimal set of tuples justifying the result, with semantics based on semiring provenance for first-order logic. On a benchmark of production-inspired workloads over restaurant review and customer support datasets, Evergreen's optimized configurations occupy the entire cost-quality Pareto frontier. With a strong LLM, Evergreen preserves verification quality at an F1 of 0.94 while reducing cost by 3.1x relative to unoptimized verification; with a substantially weaker LLM, it surpasses the strongest external baseline's F1 (0.87 vs. 0.83) at 7.0x lower cost.

Alexander W. Lee, Benjamin Han, Shayak Sen +3

Brown University · Snowflake Inc.

LLM Inference Efficiency Claim Verification

Apr 28, 2026cs.MA

Pythia: Exploiting Workflow Predictability for Efficient Agent-Native LLM Serving

As LLM applications grow more complex, developers are increasingly adopting multi-agent architectures to decompose workflows into specialized, collaborative components, introducing structure that constrains agent behavior and exposes useful semantic predictability. Unlike traditional LLM serving, which operates under highly dynamic and uncertain conditions, this structured topology enables opportunities to reduce runtime uncertainty

\unicode{x2015}

yet existing systems fail to exploit it, treating agentic workloads as generic traffic and incurring significant inefficiencies. Our analysis of production traces from an agent-serving platform and an internal coding assistant reveals key bottlenecks, including low prefix cache hit rates, severe resource contention from long-context requests, and substantial queuing delays due to suboptimal scaling. To address these challenges, we propose Pythia, a multi-agent serving system that captures workflow semantics through a simple interface at the serving layer, unlocking new optimization opportunities and substantially improving throughput and job completion time over state-of-the-art baselines.

Shan Yu, Junyi Shu, Yuanjiang Ni +14

UCLA · Alibaba Cloud Computing · Alibaba Group +6

LLM Inference Efficiency Multi-Agent LLM Systems LLM Serving LLM Agent Workflow Optimization LLM Agent Serving

Apr 27, 2026cs.LG

PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference

We present PolyKV, a system in which multiple concurrent inference agents share a single, asymmetrically compressed KV cache pool. Rather than allocating a separate KV cache per agent -- the standard paradigm -- PolyKV writes a compressed cache once and injects it into N independent agent contexts via HuggingFace DynamicCache objects. Compression is asymmetric: Keys are quantized at int8 (q8_0) to preserve softmax stability, while Values are compressed using TurboQuant MSE -- a Fast Walsh-Hadamard Transform (FWHT) rotation followed by 3-bit Lloyd-Max quantization with centroids tuned to N(0,1). We evaluate across two model scales (SmolLM2-1.7B-Instruct and Llama-3-8B-Instruct), three context lengths (600-7,194 tokens), and up to 15 concurrent agents. PolyKV achieves a stable 2.91x compression ratio across all configurations. On Llama-3-8B with 15 agents sharing a 4K-token context, PolyKV reduces KV cache memory from 19.8 GB to 0.45 GB -- a 97.7% reduction -- while maintaining only +0.57% perplexity degradation and a mean BERTScore F1 of 0.928. PPL delta does not grow with agent count and improves as context length increases, inverting to -0.26% at 1,851 coherent tokens. To our knowledge, no prior work combines a single shared, lossy-compressed KV pool with multi-reader concurrent agent access.

Ishan Patel, Ishan Joshi

Independent Researcher

LLM Inference Efficiency Multi-Agent LLM Systems KV Caching KV-Cache Reuse KV-Cache Compression KV-Cache Quantization

Apr 27, 2026cs.DC

GLM-5 Serving Parameter Tuning for OpenClaw: Single-Deployment MaaS Inference Optimization for Long-Context Agent Workloads

OpenClaw requests are dominated by long, tool-augmented prefixes, including system prompts, conversation history, and tool outputs fed back into the context window. For this workload, with about 28k-30k input tokens and 500 output tokens per request, serving quality is governed by throughput, TTFT, and tail latency rather than short-prompt throughput alone. This report studies GLM-5 serving-parameter tuning within a MaaS multi-model inference optimization architecture. The scope is the Single-Node Optimization block of the inference-optimization layer, where chunked prefill, tensor parallelism (TP), pipeline parallelism (PP), and request concurrency are tuned for one GLM-5 serving deployment; in this report, "Single-Node Optimization" denotes the architecture block, while experiments run on a two-node, sixteen-GPU cluster. Within the tested space, the best configuration is chunked-prefill-size=3072, tp=4, pp-size=4, and max-running-requests=24. Compared with the conservative 2048/4/4/16 baseline, it increases request throughput from 0.43 to 0.48 req/s and total token throughput from 9029.64 to 9993.23 tok/s, while reducing average TTFT from 8.98 to 6.69 s and latency P90 from 40.23 to 32.64 s. Under the same hardware footprint, this corresponds to an estimated 10.4% lower serving cost per request and 9.6% lower cost per token. The results show that the optimum is workload-specific: larger chunk sizes and deeper queueing do not monotonically improve performance. We therefore recommend 3072 / tp4 / pp4 / max24 as the default OpenClaw deployment profile.

Minjie Hua, Ning Wang, Peijun Yang +2

China Unicom

LLM Inference Efficiency LLM Serving Long-Context Language Model Inference Tensor Parallelism

Apr 27, 2026cs.CY

Latency and Cost of Multi-Agent Intelligent Tutoring at Scale

Multi-agent LLM tutoring systems improve response quality through agent specialization, but each student query triggers several concurrent API calls whose latencies compound through a parallel-phase maximum effect that single-agent systems do not face. We instrument ITAS, a four-agent tutoring system built on Gemini 2.5 Flash and Google Vertex AI, across three throughput tiers (Standard PayGo, Priority PayGo, and Provisioned Throughput) and eleven concurrency levels up to 50 simultaneous users, producing over 3,000 requests drawn from a live graduate STEM deployment. Priority PayGo maintains flat sub-4-second response times across the full load range; Standard PayGo degrades substantially under classroom-scale concurrency; and Provisioned Throughput delivers the lowest latency at low concurrency but saturates its reserved capacity above approximately 20 concurrent users. Cost analysis places both pay-per-token tiers well below the price of a STEM textbook per student per semester under a worst-case usage ceiling. Provisioned Throughput, expensive under continuous provisioning, becomes cost-competitive for institutions that can predict and concentrate their traffic toward high utilization. These results provide concrete tier-selection guidance across deployment scales from a single seminar to a university-wide rollout.

Iizalaarab Elhaimeur, Nikos Chrisochoides

Center for Real-Time Computing · Computer Science Department · Old Dominion University +2

LLM Inference Efficiency Multi-Agent LLM Systems LLM Serving Intelligent Tutoring Systems

Apr 25, 2026cs.HC

Scalable LLM-based Coding of Dialogue in Healthcare Simulation: Balancing Coding Performance, Processing Time, and Environmental Impact

Research shows that dialogue, the interactive process through which participants articulate their thinking, plays a central role in constructing shared understanding, coordinating action, and shaping learning outcomes in teams. Analysing dialogue content has been central to advancing team learning theory and informing the design of computer-supported collaborative learning environments, yet this progress has depended on labour-intensive qualitative coding. LLMs offer new possibilities for automating and enhancing the dialogue layer within emerging multimodal learning analytics approaches, with recent studies showing that they can approximate human coding through few-shot prompting. However, prior work has focused on replicating human coding accuracy for research purposes, rather than addressing a more educationally consequential question: how can we design prompts that allow an LLM to label team dialogue accurately and fast enough to be useful in real settings, such as in-person healthcare simulations, where results must be returned quickly and computational cost and sustainability also matter? This paper investigates how prompt design and batching strategies can be optimised to balance coding accuracy, processing time, and environmental impact in team-based healthcare simulation debriefing. Using a dataset of 11,647 utterances coded across 6 dialogue constructs, we compared 4 prompt designs across varying batch sizes, evaluating coding performance, processing time, and energy consumption, as well as the trade-offs between these metrics. Results indicate that increasing batch size improves speed and reduces energy use, but negatively impacts coding performance. Beyond demonstrating the feasibility of LLM-based qualitative analysis, this study offers practical guidance for scaling dialogue analytics in contexts where timeliness, privacy, and sustainability are critical.

Kiyoshige Garces, Gloria Milena Fernandez-Nieto, Linxuan Zhao +4

RMIT University · Monash University · Adelaide University +2

LLM Inference Efficiency LLM Prompting LLM-Assisted Annotation

Apr 24, 2026cs.AI

PExA: Parallel Exploration Agent for Complex Text-to-SQL

LLM-based agents for text-to-SQL often struggle with latency-performance trade-off, where performance improvements come at the cost of latency or vice versa. We reformulate text-to-SQL generation within the lens of software test coverage where the original query is prepared with a suite of test cases with simpler, atomic SQLs that are executed in parallel and together ensure semantic coverage of the original query. After iterating on test case coverage, the final SQL is generated only when enough information is gathered, leveraging the explored test case SQLs to ground the final generation. We validated our framework on a state-of-the-art benchmark for text-to-SQL, Spider 2.0, achieving a new state-of-the-art with 70.2% execution accuracy.

Tanmay Parekh, Ella Hofmann-Coyle, Shuyi Wang +3

University of California Los Angeles · Bloomberg

LLM Inference Efficiency Text-to-SQL LLM Agents

Apr 24, 2026cs.CL

EverydayGPT: Confidence-Gated Routing for Efficient and Safe Hybrid GPT-RAG Conversational QA

Standard Retrieval-Augmented Generation (RAG) pipelines route every query through retrieval and generation unconditionally, incurring unnecessary computation and propagating low-quality context to the generator. We introduce EverydayGPT, a lightweight conversational QA system built around a Confidence-Gated Routing (CGR) mechanism that formalises the routing decision as a joint policy over retrieval distance and extraction adequacy. The backbone is a 205M-parameter GPT trained from scratch on 10B tokens of FineWeb-Edu. CGR avoids invoking the costly GPT pathway (~5.9s) for 85 percent of queries by resolving them via fast RAG extraction (~45 ms), yielding over 120x latency reduction on the majority of queries while maintaining answer quality. On a 500-question in-domain benchmark, the system achieves F1 = 0.226 +/- 0.004 compared to 0.171 for GPT-only and 0.210 for unconditional RAG. Gains over strong baselines are modest but consistent, while efficiency improvements are substantial (6.3x mean latency reduction). A structured grounding audit finds no unsupported claims in the sampled set, with explicit scope limitations. We position this work as a study of routing strategies under resource constraints rather than a claim of state-of-the-art performance.

Jaspreet Singh Nahal

B.Tech Computer Science Engineering (Artificial Intelligence) Dr. A.P.J. Abdul Kalam Technical University, Delhi, India

LLM Inference Efficiency Retrieval-Augmented Generation Adaptive RAG Question Answering LLM Routing

Apr 23, 2026cs.LG

Sub-Token Routing for KV Cache Compression

Transformer inference often requires a large KV cache, especially for long-context language modeling and multimodal generation. Existing compression methods usually reduce cache cost by selecting, evicting, quantizing, or compressing cached tokens, or by reducing the visual-token sequence before language-model inference. We introduce sub-token routing, a KV-compression method that adds a finer control axis inside retained tokens. It splits each retained value vector into groups and keeps only selected groups, while leaving query and key states unchanged. The method is designed to work after token-level reduction. First, a token-reduction method determines which tokens are retained. Then, sub-token routing compresses the value states inside those retained tokens. Experiments under matched KV budgets show that adding sub-token routing improves token-level reduction performance in both LLM and VLM settings, including Quest on LLaMA-2-7B and Qwen2.5-7B, and FastV/VisionZip across LLaVA and Qwen-VL models. The gains are larger at smaller KV budgets, suggesting that value-group routing is especially useful when further token removal becomes costly. Overall, token-level reduction and sub-token routing provide complementary ways to reduce KV cost.

Wei Jiang, Wei Wang

Futurewei Technologies San Jose, CA 95131, USA

LLM Inference Efficiency KV Caching Efficient VLM Inference KV-Cache Compression

Apr 22, 2026cs.CL

TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping

The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling LRMs to reason longer, and more accurately. However, a growing body of studies show that LRMs are still inefficient, over-generating verification and reflection steps. Additionally, the high-level role of each reasoning step and how different step types contribute to the generation of correct answers, is largely underexplored. To address this challenge, we introduce TRACES (Tagging of the Reasoning steps enabling Adaptive Cost-Efficient early-Stopping), a lightweight framework that tags reasoning steps in real-time, and enable adaptive, cost-efficient early stopping of large-language-model inferences. Building on this framework we monitor reasoning behaviors during inferences, and we find that LRMs tend to shift their reasoning behavior after reaching a correct answer. We demonstrate that the monitoring of the specific type of steps can produce effective interpretable early stopping criteria. We evaluate the TRACES framework on three mathematical reasoning benchmarks, namely, MATH500, GSM8K, AIME and two knowledge and reasoning benchmarks, MMLU and GPQA respectively. We achieve 20 to 50% token reduction while maintaining comparable accuracy to standard generation.

Yannis Belkhiter, Seshu Tirupathi, Giulio Zizzo +1

IBM Research Europe · Trinity College Dublin · Dublin, Ireland +1

LLM Inference Efficiency Early Stopping Efficient Language Model Reasoning Efficient Language Model Inference LLM Reasoning Large Reasoning Models+1

Apr 22, 2026cs.LG

RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory

Large language models cache all previously computed key-value (KV) pairs during generation, and this KV cache grows linearly with sequence length, making it a primary memory bottleneck for serving. Quantizing the KV cache to fewer bits reduces this cost, yet all current quantizers assign the same bit-width to every attention head, ignoring the large variation in head importance. A natural idea is to allocate more bits to important heads and fewer to the rest. We show, however, that such mixed-precision allocation has a hidden pitfall: each quantizer follows a different distortion curve D(b)=alpha*beta^{-b}, and the decay rate beta varies from 3.6 to 5.3 across quantizer designs. Applying one quantizer's distortion model to another inverts the allocation order and makes performance worse than uniform quantization. We call this failure mode distortion model mismatch and propose RateQuant to resolve it. RateQuant fits a per-quantizer distortion model from a small calibration set, then solves the resulting bit-allocation problem in closed form via reverse waterfilling from rate-distortion theory. On Qwen3-8B at 2.5 average bits, calibrated RateQuant reduces KIVI's perplexity from 49.3 to 14.9 (70% reduction) and improves QuaRot by 6.6 PPL. The entire calibration takes 1.6 s on a single GPU and adds zero overhead at inference time.

Fei Zuo, Zikang Zhou, Hao Cong +2

1BA TechWorks (BMW Group) · 2National University of Singapore · 3Tsinghua University

LLM Inference Efficiency Mixed-Precision Quantization LLM Quantization KV Caching Memory-Efficient Optimization Rate-Distortion Optimization+1

Apr 21, 2026cs.CL

Are Large Language Models Economically Viable for Industry Deployment?

Generative AI-powered by Large Language Models (LLMs)-is increasingly deployed in industry across healthcare decision support, financial analytics, enterprise retrieval, and conversational automation, where reliability, efficiency, and cost control are critical. In such settings, models must satisfy strict constraints on energy, latency, and hardware utilization-not accuracy alone. Yet prevailing evaluation pipelines remain accuracy-centric, creating a Deployment-Evaluation Gap-the absence of operational and economic criteria in model assessment. To address this gap, we present EDGE-EVAL-a industry-oriented benchmarking framework that evaluates LLMs across their full lifecycle on legacy NVIDIA Tesla T4 GPUs. Benchmarking LLaMA and Qwen variants across three industrial tasks, we introduce five deployment metrics-Economic Break-Even (Nbreak), Intelligence-Per-Watt (IPW ), System Density (\r{ho}sys), Cold-Start Tax (Ctax), and Quantization Fidelity (Qret)-capturing profitability, energy efficiency, hardware scaling, serverless feasibility, and compression safety. Our results reveal a clear efficiency frontier-models in the <2B parameter class dominate larger baselines across economic and ecological dimensions. LLaMA-3.2-1B (INT4) achieves ROI break-even in 14 requests (median), delivers 3x higher energy-normalized intelligence than 7B models, and exceeds 6,900 tokens/s/GB under 4-bit quantization. We further uncover an efficiency anomaly-while QLoRA reduces memory footprint, it increases adaptation energy by up to 7x for small models-challenging prevailing assumptions about quantization-aware training in edge deployment.

Abdullah Mohammad, Sushant Kumar Ray, Pushkar Arora +5

DSEU-Okhla, New Delhi, India · University of Delhi, New Delhi, India · 6, 8Macquarie University, Sydney, Australia +1

LLM Inference Efficiency LLM Evaluation Cost-Aware Inference

Apr 21, 2026cs.AI

How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning

Reasoning-capable large language models solve hard problems by emitting long chains of thought, paying heavily in latency, GPU time, and energy. Casual inspection of their traces reveals extensive reformulation, verification, and circular self-reflection, yet how much of this deliberation is actually necessary has never been measured at scale or explained from first principles. This paper closes both gaps. We formalise reasoning redundancy directly in terms of the reasoning model itself: the redundancy of a correct trace is the largest fraction of its trailing segmented steps that can be truncated while

π

, forced to terminate thinking and emit a final answer, still produces the correct answer. A large-scale quantification across four frontier reasoning models and two mathematical benchmarks shows that step-level redundancy is consistently high -- between 61% and 93% across the 8 (model, benchmark) conditions we study, with the median critical prefix equal to a single segmented step in six of the eight conditions -- that the finding is robust to the choice of judge family, and that although

ρ

decreases with problem difficulty on MATH-500, all four models remain substantially redundant (

ρ\in [46\%, 85\%]

) even on the hardest Level-5 problems. We then prove that this redundancy is a structural consequence of length-agnostic outcome rewards, not a model-specific artefact: under any such reward, no finite expected stopping time is optimal. The result holds regardless of RL algorithm, base model, data distribution, or whether the policy is obtained via RL or distillation; over-thinking is therefore not a bug to be patched in individual models but a structural property of how current reasoning models are trained. Code: https://github.com/zhiyuanZhai20/how-much-thinking-is-enough

Zhiyuan Zhai, Xinkai You, Wenjing Yan +1

Fudan University · The Chinese University of Hong Kong

LLM Inference Efficiency RL for Language Model Reasoning Efficient Language Model Reasoning LLM Mathematical Reasoning LLM Reasoning Large Reasoning Models+1

Apr 20, 2026cs.CL

Learning to Seek Help: Dynamic Collaboration Between Small and Large Language Models

Large language models (LLMs) offer strong capabilities but raise cost and privacy concerns, whereas small language models (SLMs) facilitate efficient and private local inference yet suffer from limited capacity. To synergize the complementary strengths, we introduce a dynamic collaboration framework, where an SLM learns to proactively decide how to request an LLM during multi-step reasoning, while the LLM provides adaptive feedback instead of acting as a passive tool. We further systematically investigate how collaboration strategies are shaped by SLM and LLM capabilities as well as efficiency and privacy constraints. Evaluation results reveal a distinct scaling effect: stronger SLMs become more self-reliant, while stronger LLMs enable fewer and more informative interactions. In addition, the learned dynamic collaboration strategies significantly outperform static pipelines and standalone inference, and transfer robustly to unseen LLMs.

Hang Zeng, Xiangyu Liu, Yong Hu +5

Shanghai Jiao Tong University, Shanghai, China · WeChat Tencent, Beijing, China · State University of New York at Buffalo, New York, United States.

LLM Inference Efficiency Small Language Models Multi-LLM Collaboration

Apr 19, 2026cs.LG

SLO-Guard: Crash-Aware, Budget-Consistent Autotuning for SLO-Constrained LLM Serving

Serving large language models under latency service-level objectives (SLOs) is a configuration-heavy systems problem with an unusually failure-prone search space: many plausible configurations crash outright or miss user-visible latency targets, and standard black-box optimizers treat these failures as wasted trials. We present SLO-Guard, a crash-aware autotuner for vLLM serving that treats crashes as first-class observations. SLO-Guard combines a feasible-first Thermal Budget Annealing (TBA) exploration phase with a warm-started Tree-structured Parzen Estimator (TPE) exploitation phase; the handoff replays all exploration history, including crashes encoded as extreme constraint violations. We additionally contribute a configuration-repair pass, a GPU-aware KV-cache memory guard, and a four-category crash taxonomy. We evaluate SLO-Guard on Qwen2-1.5B served with vLLM 0.19 on an NVIDIA A100 40GB. Across a pre-specified five-seed study, both SLO-Guard and uniform random search attain 75/75 feasibility with zero crashes under the corrected concurrent harness, and are statistically tied on best-achieved latency (Mann-Whitney two-sided p=0.84). SLO-Guard's advantage is in budget consistency: more trials in the fast-serving regime (10.20 vs. 7.40 out of 15; one-sided p=0.014) and higher post-handoff consistency (0.876 vs. 0.539; p=0.010). Under concurrent load, SLO-Guard's cross-seed standard deviation on best latency is 4.4x tighter than random search's (2.26 ms vs. 10.00 ms). A harness-replication analysis shows that the consistency findings survive an independent sequential-dispatch measurement condition. The central claim is not that SLO-Guard finds a better final configuration, but that it spends a fixed tuning budget more predictably once the fast regime has been found.

Christian Lysenstøen

Inland Norway University of Applied Sciences · Visiting Student, University of California, Berkeley

LLM Inference Efficiency LLM Serving Bayesian Optimization Black-Box Optimization

Apr 19, 2026cs.CL

ONTO: A Token-Efficient Columnar Notation for LLM Input Optimization

Serialization formats designed for document interchange impose structural overhead that becomes prohibitive when large language models consume operational data at scale. A modest dataset of 1,000 IoT sensor readings serialized as JSON requires approximately 80,000 tokens - the majority spent on repeated field names, nested braces, and structural punctuation rather than semantic content. We present ONTO (Object Notation for Token Optimization), a columnar notation that declares field names once per entity and arranges values in pipe-delimited rows with indentation-based hierarchy. This schema-once, data-many design eliminates per-record key repetition while preserving human readability and nested structure support. Evaluation across three synthetic operational datasets demonstrates 46-51% token reduction versus JSON, with stable scaling from 100 to 1,000 records. Controlled inference benchmarks on Qwen2.5-7B show corresponding 5-10% latency improvement. Comprehension validation confirms no material degradation in LLM task accuracy across lookup, counting, extraction, and aggregation operations when format context is provided. Ablation analysis reveals that key repetition accounts for the majority of JSON overhead, with indentation costs in nested structures explaining the 4-percentage-point gap between flat and hierarchical data. ONTO occupies a previously unfilled position in the serialization landscape: columnar efficiency with hierarchical structure, optimized for LLM context windows rather than document interchange. Code and specification are available at https://github.com/harsh-aranga/onto.

Harshavardhanan Deekeswar

Independent Researcher · Chennai, India

LLM Inference Efficiency Token Efficiency