The paper reports on Grayhat Developers’ experience deploying a hybrid AI stack that combines local open‑source models with commercial agents. After finding local models too slow for complex coding tasks, the team kept commercial agents for those tasks while using local models for lower‑complexity work, documentation sync, and tool coordination, reducing commercial AI usage by 27–36%. The initial self‑hosted deployment suffered from UX friction, but a centrally configured deployment improved adoption.
arXiv:2608. 00101v1 Announce Type: cross Abstract: AI coding agents like GitHub Copilot, Claude Code, and Codex interleave multi-step LLM inference with tool execution, creating a workload different from chatbots.
The paper investigates how large‑language‑model (LLM) based AI agents mix latency, local resource usage, and container bottlenecks when processing user requests that involve remote LLM calls and local tool execution. By measuring three representative tasks—retrieval‑augmented question answering, web search, and software coding—the authors show that agents exhibit diverse resource dynamics, with concurrent requests revealing task‑specific bottlenecks in CPU, disk I/O, and memory. Leveraging these insights, they propose CPU‑aware tool admission and task‑aware CPU allocation, achieving up to a 5.4× speed‑up for CPU‑sensitive tasks and a 32% reduction in average latency across multiple tasks.
arXiv:2610.22732v1 Announce Type: new Abstract: Advances in frontier coding agents have sharply increased the token costs of AI-assisted software engineering. Their token efficiency is typically eval...
arXiv:2607. 13034v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires.
The paper investigates how the distribution of capacity and task information across stages of AI production affects the economic value of inference. Using controlled workflow experiments on software‑engineering tasks, it finds that direct execution achieves a 59.6% success rate at token ceilings of 12,000 and 24,000, while information‑constrained planning improves from 36.2% to 51.2%. The study also shows that giving planners access to task issues boosts success, and that scaling token limits changes the balance between planning and execution workloads.
arXiv:2608. 04968v1 Announce Type: new Abstract: The capabilities of an LLM agent depend not only on its model but on the harness: the executable program that constructs context, invokes tools, verifies results, and recovers from failure.
arXiv:2607. 13080v1 Announce Type: cross Abstract: Autonomous coding agents force engineering organizations to choose between API-based frontier models -- strong reasoning at high token cost -- and on-premise quantized open-weights models, which promise low-marginal-cost scaling and data sovereignty at some loss of reasoning fidelity.
The paper examines how AI coding agents are evolving beyond simple autocomplete to perform complex tasks such as repository inspection, multi-file editing, tool execution, test writing, pull request creation, and long-duration work with minimal supervision. It highlights that while these agents boost coding activity, significant bottlenecks remain in review, integration, testing, security, deployment, and production operations, and that the economics of software development are shifting toward variable token, tool, sandbox, CI, and rework costs. The authors synthesize recent research and industry data to propose four engineering concepts—Agentic SDLC Throughput Paradox, Production-Qualified Change, Verification Tax, and an Agentic SDLC Control Plane—to guide the allocation of autonomy within cost, reliability, and human-attention constraints, ultimately reframing the research focus to production-qualified value per dollar, reviewer-hour, and operational risk.
The paper introduces CTXAgent, a self‑controlled context management system for large language model agents that compacts conversation history when a token threshold is reached. It evaluates seven frontier models, comparing their ability to manage context with and without dedicated tools, and benchmarks performance across coding, scientific, and software engineering tasks. Results show that well‑managed models keep live context below 100k tokens, maintain high benchmark scores, and achieve significant cost reductions, with Claude Opus 5.5 outperforming its explicit configuration by 34% lower cost.
arXiv:2607. 22948v1 Announce Type: cross Abstract: The ORBIT (Operations Responses and Business Intelligence Toolkit) project was initiated to assess agentic AI for the upcoming ESnet 7 initiative and to address persistent operational pain points in the Network Operations Center (NOC) workflow.
arXiv:2608.27969v2 Announce Type: replace Abstract: Long-horizon coding agents operate over evolving repository states while increasingly relying on heterogeneous capabilities, delegated agents, and...
arXiv:2606. 14350v1 Announce Type: cross Abstract: Artificial Intelligence (AI) systems must typically satisfy service-level objectives including accuracy, latency, and cost.