OpenAI Blog
Jan 23
Unrolling the Codex agent loop
A technical deep dive into the Codex agent loop, explaining how Codex CLI orchestrates models, tools, prompts, and performance using the Responses API.
Speeding up agentic workflows with WebSockets in the Responses API
A deep dive into the Codex agent loop, showing how WebSockets and connection-scoped caching reduced API overhead and improved model latency.
Related stories
arXiv AI
Aug 18
Learning Agent Execution for KV-Cache Management in Agentic Serving
arXiv:2608. 14624v1 Announce Type: new Abstract: Multi-agent LLM systems have emerged as an important deployment paradigm for AI services, where each user request is decomposed into a sequence of specialized agents.
arXiv AI
Jun 30
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
arXiv:2606. 30560v1 Announce Type: cross Abstract: Coding agents are rapidly becoming a major application of agentic LLMs, but serving them efficiently remains challenging.
arXiv AI
Jul 24
Workload-Aware Caching for Multi-Agent Systems
arXiv:2607. 20495v1 Announce Type: new Abstract: Multi-agent systems decompose complex tasks into directed acyclic graphs (DAGs) of specialized agent executions, creating natural opportunities for caching intermediate results across queries.
arXiv AI
Jun 6
SentinelBench: A Benchmark for Long-Running Monitoring Agents
arXiv:2606. 05342v1 Announce Type: new Abstract: AI agents are increasingly asked to carry out work that spans minutes, hours, or longer.
arXiv Machine Learning
Aug 4
Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale
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.
arXiv Machine Learning
Sep 15
AgentKV: Phase-Aware KV Eviction for Agentic LLMs
arXiv:2609.14872v1 Announce Type: new Abstract: Agentic serving can consume orders of magnitude more tokens than chatbot workloads, stressing both KV-cache capacity and decode-time bandwidth. Most KV...
arXiv AI
Jun 19
Beyond Static Endpoints: Tool Programs as an Interface for Flexible Agentic Web Services
arXiv:2606. 19992v1 Announce Type: cross Abstract: In the agentic web era, LLM-based agents increasingly invoke web services as tools, yet most interfaces remain \emph{static endpoints} that poorly express long-horizon workflows with loops, conditionals, joins, and retries.
arXiv AI
Jun 6
Do More Agents Help? Controlled and Protocol-Aligned Evaluation of LLM Agent Workflows
arXiv:2606. 05670v1 Announce Type: new Abstract: Does adding more agents help an LLM workflow once compared systems share the same benchmark loader, tool access, answer contract, usage accounting, and trajectory logging?
OpenAI Blog
Sep 10
Introducing the Agents API
Build and launch cloud agents with the Agents API, a managed service powered by the Codex harness for orchestration, long-running sessions, and tool use.
arXiv AI
Aug 18
From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems
arXiv:2608. 15127v1 Announce Type: cross Abstract: Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and persistent state.
arXiv AI
Sep 18
Not All AI Agents Are Equal: Characterizing Resource and Performance Dynamics
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.