Saved in:
Bibliographic Details
Main Authors: Amini, Soufiane, Benajiba, Yassine, Bernardis, Cesare, Cayet, Paul, Chafi, Hassan, Fathan, Abderrahim, Faucon, Louis, Hilloulin, Damien, Hong, Sungpack, Kossyk, Ingo, Le, Tran Minh Son, Patra, Rhicheek, Ravi, Sujith, Schweizer, Jonas, Singh, Jyotika, Singh, Shailender, Sun, Weiyi, Talamadupula, Kartik, Xu, Jerry
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.04173
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908634930216960
author Amini, Soufiane
Benajiba, Yassine
Bernardis, Cesare
Cayet, Paul
Chafi, Hassan
Fathan, Abderrahim
Faucon, Louis
Hilloulin, Damien
Hong, Sungpack
Kossyk, Ingo
Le, Tran Minh Son
Patra, Rhicheek
Ravi, Sujith
Schweizer, Jonas
Singh, Jyotika
Singh, Shailender
Sun, Weiyi
Talamadupula, Kartik
Xu, Jerry
author_facet Amini, Soufiane
Benajiba, Yassine
Bernardis, Cesare
Cayet, Paul
Chafi, Hassan
Fathan, Abderrahim
Faucon, Louis
Hilloulin, Damien
Hong, Sungpack
Kossyk, Ingo
Le, Tran Minh Son
Patra, Rhicheek
Ravi, Sujith
Schweizer, Jonas
Singh, Jyotika
Singh, Shailender
Sun, Weiyi
Talamadupula, Kartik
Xu, Jerry
contents The proliferation of agent frameworks has led to fragmentation in how agents are defined, executed, and evaluated. Existing systems differ in their abstractions, data flow semantics, and tool integrations, making it difficult to share or reproduce workflows. We introduce Open Agent Specification (Agent Spec), a declarative language that defines AI agents and agentic workflows in a way that is compatible across frameworks, promoting reusability, portability and interoperability of AI agents. Agent Spec defines a common set of components, control and data flow semantics, and schemas that allow an agent to be defined once and executed across different runtimes. Agent Spec also introduces a standardized Evaluation harness to assess agent behavior and agentic workflows across runtimes - analogous to how HELM and related harnesses standardized LLM evaluation - so that performance, robustness, and efficiency can be compared consistently across frameworks. We demonstrate this using four distinct runtimes (LangGraph, CrewAI, AutoGen, and WayFlow) evaluated over three different benchmarks (SimpleQA Verified, $τ^2$-Bench and BIRD-SQL). We provide accompanying toolsets: a Python SDK (PyAgentSpec), a reference runtime (WayFlow), and adapters for popular frameworks (e.g., LangGraph, AutoGen, CrewAI). Agent Spec bridges the gap between model-centric and agent-centric standardization & evaluation, laying the groundwork for reliable, reusable, and portable agentic systems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_04173
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Open Agent Specification (Agent Spec): A Unified Representation for AI Agents
Amini, Soufiane
Benajiba, Yassine
Bernardis, Cesare
Cayet, Paul
Chafi, Hassan
Fathan, Abderrahim
Faucon, Louis
Hilloulin, Damien
Hong, Sungpack
Kossyk, Ingo
Le, Tran Minh Son
Patra, Rhicheek
Ravi, Sujith
Schweizer, Jonas
Singh, Jyotika
Singh, Shailender
Sun, Weiyi
Talamadupula, Kartik
Xu, Jerry
Artificial Intelligence
The proliferation of agent frameworks has led to fragmentation in how agents are defined, executed, and evaluated. Existing systems differ in their abstractions, data flow semantics, and tool integrations, making it difficult to share or reproduce workflows. We introduce Open Agent Specification (Agent Spec), a declarative language that defines AI agents and agentic workflows in a way that is compatible across frameworks, promoting reusability, portability and interoperability of AI agents. Agent Spec defines a common set of components, control and data flow semantics, and schemas that allow an agent to be defined once and executed across different runtimes. Agent Spec also introduces a standardized Evaluation harness to assess agent behavior and agentic workflows across runtimes - analogous to how HELM and related harnesses standardized LLM evaluation - so that performance, robustness, and efficiency can be compared consistently across frameworks. We demonstrate this using four distinct runtimes (LangGraph, CrewAI, AutoGen, and WayFlow) evaluated over three different benchmarks (SimpleQA Verified, $τ^2$-Bench and BIRD-SQL). We provide accompanying toolsets: a Python SDK (PyAgentSpec), a reference runtime (WayFlow), and adapters for popular frameworks (e.g., LangGraph, AutoGen, CrewAI). Agent Spec bridges the gap between model-centric and agent-centric standardization & evaluation, laying the groundwork for reliable, reusable, and portable agentic systems.
title Open Agent Specification (Agent Spec): A Unified Representation for AI Agents
topic Artificial Intelligence
url https://arxiv.org/abs/2510.04173