Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling
This paper introduces agent just-in-time (JIT) compilation as an alternative to the sequential fetch-screenshot-execute loop used by current computer-use agents. The approach compiles natural language task descriptions directly into executable code that can include LLM calls, tool calls, and parallelization, using three components: JIT-Planner, JIT-Scheduler, and an invariant-enforcing tool protocol. Across five web applications, JIT-Planner achieves 10.4× speedup and +28% accuracy over Browser-Use, while JIT-Scheduler achieves 2.4× speedup and +9% accuracy over OpenAI CUA.
Related guides (4)
Related events (8)
Introducing Agents.js: Give tools to your LLMs using JavaScript
Hugging Face released Agents.js, a JavaScript library that enables developers to equip large language models with tools and build agent workflows in a JS/TS environment. The library brings tool-use and agent orchestration capabilities—previously more common in Python ecosystems—to the JavaScript developer community. It integrates with Hugging Face's model hub and inference APIs.
GLM-5.1 Open-Weights Model Targets Long-Running Agentic Tasks; Andrew Ng on Coding Agent Acceleration by Software Domain
Z.ai released GLM-5.1, an open-weights mixture-of-experts LLM (754B total / 40B active parameters) designed for sustained agentic coding tasks lasting up to eight hours, featuring iterative planning-execution-evaluation loops with thousands of tool calls. The model claims top open-weights performance on Artificial Analysis Intelligence Index and SWE-Bench Pro, available under MIT license via HuggingFace. The accompanying editorial by Andrew Ng offers a tiered framework for how much coding agents accelerate different software work categories—frontend most, then backend, infrastructure, and research least—with practical implications for team organization. A secondary item references data-center opposition and LLM helpfulness failure modes.
Coding Agents Accelerate Some Software Tasks More Than Others
Andrew Ng offers a practitioner framework ranking how much coding agents accelerate different software work: frontend development benefits most (agents close the loop via browser feedback), followed by backend, infrastructure, and research in decreasing order. Backend work still requires skilled developers to handle corner cases and security; infrastructure decisions remain largely human-driven due to complex tradeoffs and limited LLM knowledge in that domain; research is least accelerated because ideation and hypothesis iteration are not primarily coding tasks. The commentary is aimed at helping engineering managers set realistic expectations and organize teams accordingly.
Speeding up agentic workflows with WebSockets in the Responses API
OpenAI published a technical deep dive into the Codex agent loop, detailing how WebSockets and connection-scoped caching were used to reduce API overhead and improve model latency. The post focuses on infrastructure optimizations within the Responses API for agentic workflows. These changes are relevant to developers building multi-step agent pipelines that rely on repeated API calls.
ProAct: Proactive Agent Architecture Using Idle-Time Compute to Anticipate User Needs
ProAct is a proactive agent architecture that uses idle time between user interactions to predict upcoming needs, pre-fetch information, and resolve knowledge gaps before queries are issued. The system analyzes dialogue history and persistent memory to iteratively acquire relevant information in advance. Evaluated on the new ProActEval benchmark (200 scenarios, 40 domains), ProAct reduces required turns by 14.8%, user effort by 11.7%, and hallucination rates by 28.1% compared to reactive baselines. The work also achieves state-of-the-art reflective accuracy on MemBench.
AgentBeats: Standardized Agent Evaluation via A2A and MCP Protocols
A new arXiv preprint proposes Agentified Agent Assessment (AAA), a framework where evaluation is performed by judge agents interacting through standardized protocols—A2A for task management and MCP for tool access—rather than bespoke benchmark harnesses. The authors introduce AgentBeats as a concrete implementation, validated through a five-month open competition with 298 judge agents and 467 subject agents across 12 categories, plus a coding-agent case study. The work addresses fragmentation in agent evaluation by decoupling assessment logic from agent implementation, enabling reproducible and interoperable benchmarking.
agent-teams-ai: multi-agent orchestration framework with kanban-style oversight
A TypeScript open-source project on GitHub implements a multi-agent system where autonomous agents handle tasks, communicate with each other, and review each other's work, while the user supervises via a kanban board. The framework supports 200+ models across 75+ LLM providers including Codex, Claude, and OpenCode. It has accumulated 1,189 stars with 56 added today, suggesting growing community interest.
AGENTSERVESIM: Hardware-aware simulator for multi-turn LLM agent serving policies
Researchers introduce AGENTSERVESIM, a simulation framework designed to evaluate serving policies for multi-turn LLM agents without requiring dedicated accelerator hardware. The simulator models program-level execution including turn dependencies, tool-induced gaps, and KV-cache residency across HBM, host DRAM, and CXL memory hierarchies. It reproduces real-system behavior within 6% error on key performance metrics while running on commodity CPUs, enabling cost-effective exploration of scheduling, routing, and cache management policies for agentic workloads.