Large Language Models (LLMs) have achieved remarkable success in natural language understanding and generation, but their deployment is constrained by high computational demands. Deploying smaller LLMs directly on the edge can circumvent this, but with degraded accuracy. Deploying smaller cloud-based big LLMs preserves performance, but at the cost of expensive per-token computation. We present a distributed inference framework, \our{}, that integrates speculative decoding (SD) across edge and cloud. A compact draft model deployed on the edge generates candidate tokens rapidly, and a large verifier model on the cloud validates these tokens in parallel. Accepted tokens are retained, while only rejections trigger verifier correction, substantially reducing the number of cloud queries. Our plug-and-play design shifts the bulk of computation to the edge, significantly lowers inference time and cloud cost, and preserves the accuracy of the big model without any retraining requirement. Our approach demonstrates a practical path toward scalable, cost-efficient, and accurate deployment of LLMs in real-world environments. Experimental results across multiple Natural Language Processing tasks using SpecBench and CNN/Dailymail datasets demonstrate that \our{} reduces the cloud model calls by $76\%$ with zero loss in accuracy as compared to the full model.
Zixi Huang, Xiheng Wang, Andrew Wang +4cs.CL cs.LG
Recently, the practice of augmenting LLM agent capability with skills has gained prevalence. We explore the cost effective adaptation of agents to novel domains by means of learning skills. Existing works focus on performance gain over cost effectiveness. As a result, little is known about what skill learning strategies save cost. We argue that among all the different skill learning methods, those that view skills as programs can achieve the best cost reduction. By executing sequences of actions deterministically, a program-augmented agent can reliably and cheaply achieve goals that would otherwise require trial and error and risk degenerate behavior over long horizons. An agent can learn at inference time by incrementally discovering these programs and equipping them for future tasks. We hypothesize that past trajectories contain enough signal to guide skill learning, even without replay or validation, provided the agent can learn to analyze them. To test our claims, we propose SpeedRunner, a coding agent that analyzes trajectories and refactors skills for better performance on future tasks. Across three different embodied environments, we show that SpeedRunner consistently achieves the frontier in learning and cost reduction while remaining robust against distribution shifts and environmental randomness.
Computer-use agents pay full frontier inference to re-derive routines their user has already performed, because an agent's memory today records what the user said, not what the user did. We compile passively captured screen activity into agent memory with a deterministic, zero-model pipeline: it segments a local capture stream into typed activity frames, bounded episodes carrying application, site, timing, input volume, and evidence pointers back to the raw rows, with no model in the loop, so the output is byte-identical, cacheable, and mechanically auditable. On one professional's single-user corpus of 128,756 frames over 51 active days, the compiler reduces a day of raw capture to a prompt-ready context block 86x smaller in 68 ms, and an agent reading that block answers questions about the day at 98.4% accuracy (Wilson 95% CI 91.7-99.7%) against an independent oracle, versus 66-80% for an LLM summary of the same capture, a mid-tier model reading the block matching a frontier one. The same compiler doubles as a demand-side cost instrument. Read off passive, pre-delegation human activity rather than agent rollouts, it supplies two parameters that agent-cost models assume but, to our knowledge, have not measured: the Routine Overhead Ratio R and the routine recurrence h. We report first values of R, a modeled upper bound, at 60-343x, and a delegable recurrence of 9.0% in-sample and 7.7% out-of-sample, for a realistic all-fleet token ceiling near 8%; a compiled routine replays deterministically with the model out of the loop, demonstrated live at zero model tokens on a guard-matched hit. Schema, compiler, and evaluation harness are open.
Large language model (LLM) cascades reduce inference cost by routing easy queries to a small model and deferring hard queries to a larger one. Production cascades govern this deferral through a confidence threshold, but LLM confidence scores are miscalibrated, the threshold must be tuned per model pair and per domain, and no setting yields a formal bound on cascade accuracy. We introduce \textbf{Conformal Cascade} (CC), a multi-tier inference framework that uses conformal prediction set size as the deferral rule: accept when the calibrated set collapses to a single answer, defer otherwise. The procedure delivers a distribution-free, finite-sample accuracy guarantee. By a per-tier union bound, the prediction set at the accepting tier covers the correct answer with probability at least $1 - Kα$ for any user-specified $α$; under a selection-preservation condition (consistent with, but not strictly implied by, our marginal coverage results), the bound tightens to $1 - α$. We further characterise expected cascade cost as an explicit function of $α$ and the calibration-set acceptance rate. Across 18 multiple-choice benchmarks spanning science, medicine, commonsense, and standardized exams, evaluated on two-tier cascades drawn from four open-weight model families, CC strictly improves over the strongest calibration-tuned heuristic cascade on the majority of family--benchmark pairs, with the largest gains on reasoning-heavy benchmarks where majority vote is unreliable; on easier benchmarks the cascade commits the vast majority of queries to the small model at no accuracy cost. Extension to open-ended generation requires an answer-clustering step that we leave for future work. The method requires no model training and only black-box API access.
Scaling LLM-based applications to millions of users is bottlenecked by the inference cost and latency of modern foundation models. A natural fix is to cluster the inputs and call the LLM only on cluster representatives, letting other members inherit the output -- but this is only safe if each member is measurably close to its representative. Existing clustering methods do not offer such per-sample quality control at scale: none jointly guarantee a minimal within-cluster similarity, exact matching of categorical attributes, and scalability to tens of millions of samples. We propose a two-stage algorithm that generates initial clusters with Mini-batch K-Means, then greedily selects representatives within each initial cluster -- a step equivalent to the Johnson-Chvatal heuristic for Set Cover over alpha-balls in embedding space. The algorithm enforces the similarity and attribute guardrails exactly by construction, and runs in $O(nd + n^2 d/K)$ time and $O(nd + n^2/K^2)$ memory for $n$ samples, feature dimension $d$, and $K$ initial clusters -- linear in $n$ when $K$ grows proportionally with $n$. We provide benchmarks against common clustering methods on internal and public datasets: our method not only delivers per-sample guardrails but also runs 10-1000x faster and scales to data sizes where most standard methods become intractable. Deployed on 38 million customers for a persona-based recommender, the clustering method cut downstream cost and latency by 50-fold while preserving personalization and unblocked the production launch.
Sebastian Koralewski, Merwan Barlier, Yulia Stolin +1cs.AI
Online recommendation platforms increasingly use Large Language Models (LLMs) to extract structured features from ad creatives. While deploying a single-call LLM annotation agent yields significant Click-Through Rate (CTR) improvements in our live production environment, per-creative prompting is prohibitively expensive to scale. The redundant system instructions sent in every request account for 94% of billed input tokens. To break this cost bottleneck, we introduce PromptPack, a scalable, high-throughput LLM annotation agent. PromptPack achieves this scale via in-context batching, combining a shared system prompt, a strict XML structural envelope, and an output correction layer to ensure deterministic, pipeline-ready feature extraction across multiple creatives simultaneously. We evaluate PromptPack via an offline retrieval benchmark using a downstream logistic-regression ranker. To deeply profile the agent's behavior, we measure AUC and introduce Volume-Weighted Absolute Lift (VWAL), a novel metric capturing the signal quality of the generated features. Compared to our live, unbatched production baseline, PromptPack at batch size 20 cuts our LLM costs by 89% and accelerates throughput by 2.5x while fully preserving AUC.
AI agents deployed for IT operations are typically permanent cost centers because every execution requires full LLM inference, even for previously solved problems. This paper introduces progressive crystallization, a lifecycle that treats agent exploration as a discovery mechanism rather than a permanent execution model. It defines a three-stage execution taxonomy, from fully agent-orchestrated to hybrid to fully deterministic workflows, together with an evidence-based promotion mechanism that converts repeatedly validated agent behaviors into cheaper and more reproducible deterministic workflows, while automatically demoting workflows that regress. Evaluated on a production cloud networking AIOps system processing tens of thousands of incidents per month, the approach increased deterministic execution from 0% to 45% over eight months, reduced per-incident agent costs by more than 70% despite doubling incident volume, and improved safety through greater reproducibility and auditability. The paper also presents the execution taxonomy, promotion and demotion criteria, trace extraction methodology, economic model, safety considerations, and discusses limitations and threats to validity.
Large language model (LLM) agents increasingly operate as multi-turn systems that must allocate context, prompt verbosity, and tool access under finite computational budgets. Static thresholds are simple, but they are brittle under heterogeneous tasks and evolving session states. We formulate resource governance as a contextual Stackelberg game: a controller commits to a quality target and a cost incentive, while an executor responds with resource actions over context, prompting, and tool usage. We learn a conditional response model, optimize a leader policy against that model, and repair the resulting policy using real-API calibration and projection onto an empirically selected action set. For the restricted game, we establish conditional guarantees for equilibrium existence, follower-response stability, safe-set projection, and transfer from a surrogate environment to the real environment under bounded value error. The primary real-API experiment comprises 300 evaluated turns. Relative to a conservative baseline, the selected repaired controller reduces mean token cost by 17.4% (Welch $p=0.022$), while the measured quality difference is not statistically significant ($p=0.44$). The theoretical results are conditional and the experiments do not estimate their regret or transfer constants; consequently, the evidence establishes a promising repaired operating point, not a certified real-system equilibrium.
Haifeng Wu, Srinivasan Manoharan, Fangbo Tu +2cs.LG
We present RLM-Cascade, a proxy-layer system that applies speculative decoding at the response level to reduce LLM API costs without requiring model architecture access or a shared vocabulary. A fast, inexpensive draft model generates a candidate response; a capable verify model accepts, enhances, or is bypassed entirely depending on a lightweight complexity router. On a real-world agentic coding workload (Claude Code), RLM-Cascade achieves a draft-use rate of 88.8% across 125 production requests, reducing API cost by 45.8% relative to a direct Opus baseline. Counter-intuitively, the proxy also reduces end-to-end latency: median response time is 2,026 ms versus 3,698 ms for Native Opus -- a 1.83X speedup at p50 -- because the SKIPPED path (DeepSeek only, no Opus call) dominates the workload distribution. Quality matches or exceeds the Opus baseline: 100% pass rate on a 20-task Code/Math/Instruct benchmark versus 95% for Native Opus. We further describe a rule-based complexity router that selects the SKIPPED path for simple agentic turns and a hybrid tool-call strategy that bypasses the speculative pipeline for schema-critical tool-selection turns. RLM-Cascade is deployed in production as an enterprise AI infrastructure component and published as open source with a live metrics dashboard and Prometheus endpoint.
Reinforcement learning (RL) post-training of Diffusion Transformers (DiTs) is prohibitively expensive, requiring thousands of high-end GPUs. Existing works explore two directions to reduce cost: seed exploration improves training convergence by selecting high-contrast samples, yet adds compute to the critical path; spot GPUs offer 69--77\% lower cost, yet sit idle during training because DiT rollouts finish nearly simultaneously, which prevents LLM-style pipelining of rollout with training. Spot preemptions further break Sequence Parallelism (SP) groups, fragmenting GPU topology. We present Spotlight, the first system that harvests spot GPUs for DiT RL post-training. Spotlight rests on two key insights we devise: (1)~we show that exploration can tolerate stale model weights because exploration that uses the model weights from the previous iteration preserves the relative ranking of random seeds, allowing exploration to run on idle spot GPUs during training. (2)~SP reconfiguration can reuse on-node state, reducing group recovery from minutes to sub-second launches. Built on these insights, Spotlight introduces three techniques: a bandit-based exploration planner that maximizes reward variance within the training time budget, elastic sequence parallelism that reconfigures SP groups on the fly via persistent schedulers and intra-node weight copying, and a preemption-aware pull-based request scheduler that balances load and commits in-flight state upon preemption. We implement Spotlight on the open-source RL platform ROLL and evaluate it on Qwen-Image post-training. Spotlight reaches the same target validation score $4\times$ faster than baselines, reducing total cost by $1.4$-$6.4\times$ while achieving superior image quality on DeepSeek-OCR and Geneval datasets with resolution $512\times512$ and $1280\times1280$.
Akshay J. Dave, David Grabaskas, Joseph A. Renevitz +1cs.AI cs.MA
Regulatory review of advanced nuclear reactor designs routinely spans more than three years and consumes hundreds of millions of dollars in combined regulator and applicant labor. We present the Regulatory Context Protocol (RCP), an Agent-to-Agent communication standard that replaces the formal human-to-human pipeline between regulators and applicants with a structured, auditable agentic channel, while preserving human oversight at safety-significant decision points. The protocol is calibrated against an analysis of 1,236 documents from U.S. Nuclear Regulatory Commission advanced reactor dockets and demonstrated with a working multi-agent pilot. Against an 89M USD, 42-month Reconstructed Baseline, RCP cuts costs by 50-77 percent (21M-44M USD) and timelines by 65 percent (15 months). Without a shared protocol, Standalone Agents reach only 54M-74M USD and 21 months. The residual cost-and-time gap is structural, not algorithmic: it traces to the inter-organizational pipeline that only an agent-to-agent standard can compress. The same bottleneck - formal multi-party review under strict auditability requirements - characterizes pharmaceutical approvals, environmental permitting, financial supervision, and aviation certification. The US regulatory paperwork burden carries a 426.5 billion USD annual opportunity cost; replicated broadly, the projected 50-77 percent reduction implies savings on the order of 210-330 billion USD per year - approaching 1 percent of US GDP.