arXiv subjects

Junfei Zhan

Publications and source records attributed to Junfei Zhan.

5 recordsLinked to original sources

arXiv2026

FDE-Bench: Evaluating LLM Agents for Deployment Environment Configuration

Deployment requires an agent to turn application code into a running system whose services connect, become ready, and remain observable. FDE-Bench evaluates this capability with 136 deployment-configuration tasks spanning Docker images, multi-service Compose stacks, and Kubernetes, in greenfield and diagnose-and-repair modes. Agents submit declarative artifacts that are collected, rebuilt, and redeployed in a pristine environment. Four gated binary check layers measure build, readiness, behavior, and conformance to the deployment specification, using programmatic checks without an LLM judge. A four-arm release gate requires a resolving reference solution and rejects tasks solved by do-nothing, specification-transcription, or generic-stub submissions. The released check annotations expose the link between 2,145 checks and their specifications, including seven documented gaps. Three additional adversarial strategies test shortcuts in the grading signals; none resolves any of the 135 tasks they cover, while a vacuous health probe passes readiness and exposes the need for downstream checks. On the 136-task evaluation grid, seven language models from four providers use the same four-tool scaffold and resolve 52.9-75.0 percent of tasks. The three zero-intelligence floors resolve none and reach a mean Deployment Score of at most 0.44. Readiness is the largest failure stage, accounting for 110 of 313 unresolved episodes. Mean resolution rate is 30.7 percentage points higher on the repair task group than on the disjoint greenfield group, with a positive gap for every model; ten tasks resist all seven. In a 25-task case study, one practicing engineer directing Claude-Sonnet-5 resolves 92 percent against 72 percent for the autonomous baseline. FDE-Bench links deployment success and failure to artifacts that can be inspected and replayed.

cs.SE↗

arXiv2026

Trains but Doesn't Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers

Post-training is becoming a service (PTaaS): a customer hands an operator data and a goal, and a forward-deployed engineer (FDE) returns a fine-tuned, evaluated, and deployed model under a budget, a human-approval gate, and reproducibility requirements. Seating an LLM agent in the FDE seat raises a question existing benchmarks cannot answer: not whether an agent can raise a metric, but whether it can be trusted to deliver. We answer it on a governed delivery plane, where an agent drives ten stages and an oracle scores each stage from platform-recorded facts. The central silent failure is the run that trains but does not learn (TBDL): loss falls, every signal stays green, and the delivered model is no better than the base. An operator-run acceptance gate catches every such run before payment, and a detector calibrated on known-corrupted runs flags severe corruption mid-run. We ran four frontier agents (Claude Opus 5, GPT-5.6-luna, Gemini 3.7 Flash, DeepSeek V4-Pro) end to end on metered L40S, A100, and H200 GPUs across 8B to 70B open bases, certifying every scenario before scoring. We also ran a human FDE arm under the same oracle and compare every agent against it.

cs.LG↗

arXiv2026

Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM Inference

Vision-Language Models (VLMs) are the perceptual backbone of embodied AI, but their energy footprint on edge hardware remains poorly understood. Existing efficiency efforts focus predominantly on reducing visual tokens, implicitly treating visual processing as the dominant energy cost. We overturn this implicit assumption through the first systematic energy profiling of on-device VLM inference, spanning five models across three architecture families, four input resolutions, and two hardware platforms (NVIDIA RTX 3070 and Jetson Orin NX). Our analysis yields three findings. First, average inference power is a model-intrinsic constant, invariant to input resolution, image complexity, and prompt type, with less than 5% variation across all conditions. This means that all energy variation across inputs must arise from variation in inference time, not from variation in power draw. Second, each output token costs 11 to 39x more wall-clock time than each input token due to the compute-bound and memory-bound asymmetry between prefill and decode, making output token count the dominant driver of both latency and energy. Third, image complexity, measured by the number of objects in an image, induces up to 4.1x energy differences at identical resolution. This variation arises not from increased visual processing cost, but from differences in output length. These findings expose a fundamental limitation of visual token pruning: even removing all visual tokens saves at most 10% of total energy for fixed-token models. Across models spanning 1 billion to 8 billion parameters, controlling output length saves up to 97% of total energy, with the energy dominance of decoding growing stronger at larger model scale. In short, the true energy bottleneck in edge VLM inference is not what the model sees, but how much it says. Code is available at https://github.com/Junfei-Z/seeing-is-free.

cs.CV↗

arXiv2026

Orchestrating Data Collection and Computation in Green IoT Networks

Future Internet of things (IoT) networks will host applications that involve data collection and computation tasks on one or more servers. To this end, this paper proposes the first mixed integer linear program (MILP) to schedule and embed applications on energy harvesting nodes, where it optimizes (i) the sampling time of devices, (ii) whether to run an application, and (iii) the energy usage of devices, gateways and servers. To ensure applications are run often, we adopt the maximum age of service (AoS) metric, and set the MILP's objective to minimize the maximum AoS or min-max AoS of applications. This paper also proposes two novel solutions: (i) a receding horizon control (RHC) based method, and (ii) a solution that greedily embeds applications according to their AoS. The results show that the min-max AoS of RHC and greedy approach is respectively 1.07x and 1.13x higher than MILP.

cs.NI↗

arXiv2025

PRISM: Privacy-Aware Routing for Adaptive Cloud-Edge LLM Inference via Semantic Sketch Collaboration

Large Language Models (LLMs) demonstrate impressive capabilities in natural language understanding and generation, but incur high communication overhead and privacy risks in cloud deployments, while facing compute and memory constraints when confined to edge devices. Cloud-edge inference has emerged as a promising paradigm for improving privacy in LLM services by retaining sensitive computations on local devices. However, existing cloud-edge inference approaches apply uniform privacy protection without considering input sensitivity, resulting in unnecessary perturbation and degraded utility even for non-sensitive tokens. To address this limitation, we propose Privacy-aware Routing for Inference with Semantic Modulation (PRISM), a context-aware framework that dynamically balances privacy and inference quality. PRISM executes in four stages: (1) the edge device profiles entity-level sensitivity; (2) a soft gating module on the edge selects an execution mode - cloud, edge, or collaboration; (3) for collaborative paths, the edge applies adaptive two-layer local differential privacy based on entity risks; and (4) the cloud LLM generates a semantic sketch from the perturbed prompt, which is then refined by the edge-side small language model (SLM) using local context. Our results show that PRISM consistently achieves superior privacy-utility trade-offs across various scenarios, reducing energy consumption and latency to 40-50% of baseline methods such as Uniform and Selective LDP, while maintaining high output quality under strong privacy constraints. These findings are validated through comprehensive evaluations involving realistic prompts, actual energy measurements, and heterogeneous cloud-edge model deployments.

cs.CR↗