New tools for building agents

Using Agents as Tools

Building manager–specialist workflows with the OpenAI Agents SDK The post Using Agents as Tools appeared first on Towards Data Science .

Introducing AgentKit, new Evals, and RFT for agents

Today, we’re releasing new tools to help developers go from prototype to production faster: AgentKit, expanded evals capabilities, and reinforcement fine-tuning for agents.

Upgrading agentic coding capabilities with the new Devstral models

Measuring Agents in Production

arXiv:2512. 04123v4 Announce Type: replace-cross Abstract: LLM-based agents already operate in production across many industries, yet we lack an understanding of what technical methods make deployments successful.

OpenEnv in Practice: Evaluating Tool-Using Agents in Real-World Environments

A Taxonomy of Architecture Options for Foundation Model-based Agents: Analysis and Decision Model

The paper presents a taxonomy of architecture options for foundation-model-based agents, covering functional capabilities, non‑functional qualities, and operational aspects of design‑time and run‑time phases. It also introduces a decision model to guide critical design and runtime choices, aiming to streamline and improve the development of such agents. By unifying these classifications, the authors seek to reduce fragmentation in the field and provide a structured framework for architects and developers.

Harness engineering: leveraging Codex in an agent-first world

By Ryan Lopopolo, Member of the Technical Staff

Build AI agents with the Mistral Agents API

Workspace agents

Learn how to build, use, and scale workspace agents in ChatGPT to automate repeatable workflows, connect tools, and streamline team operations.

AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments

arXiv:2607. 05174v1 Announce Type: new Abstract: Language agents, i.

Introducing Agents.js: Give tools to your LLMs using JavaScript

Can Agents Design Libraries for Agents?

The paper introduces LibraryDesignBench, a benchmark that tests how well agents can design reusable libraries from specifications without prescribed designs. It evaluates libraries by measuring the correctness and simplicity of programs written by three different user agents across 242 programming problems in four languages. Findings show that while agents often replicate human-designed abstractions, downstream agents still tend to reimplement library features due to rigidity or usability issues, and that providing more prescriptive guidance improves reuse and program simplicity.