$τ^τ$-Bench: An Environment for End-To-End, Realistic Agent Construction

• URL: http://arxiv.org/abs/2609.04611v1
• Date: Fri, 04 Sep 2026 01:23:47 GMT
• Title: $τ^τ$-Bench: An Environment for End-To-End, Realistic Agent Construction
• Abstract summary: We introduce $$-bench, a benchmark that makes agent construction the task.<n>A developer agent is given the records a business actually keeps, a client who holds requirements, a production API that operations must run through, and limits on serving cost and models.<n>Across 53 tasks spanning four domains, the strongest configuration, Claude Opus 5 under Claude Code, passes just 23.9% of evaluation simulations.
• Score: 20.535350290519883
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM agents are rapidly becoming production software, deployed to handle customer service, adjudicate disputes, and operate internal systems. Notably, the work of building them is increasingly handed to coding agents, yet existing benchmarks say little about whether an AI system can deliver one under the conditions of a real client engagement. We introduce $τ^τ$-bench (pronounced hyper-tau-bench), a benchmark that makes agent construction the task. A developer agent is given the records a business actually keeps, a client who holds requirements, a production API that operations must run through, a codebase to inherit, and limits on serving cost and models: the same starting point a real engagement provides. From these it must deliver a complete customer-service agent, scored by deploying that agent against held-out simulated users. Across 53 tasks spanning four domains, the strongest configuration, Claude Opus 5 under Claude Code, passes just 23.9% of evaluation simulations. Meanwhile, an expert-authored reference ceiling scores 82.2%. The failures mirror ones human agent developers see: models issue shallow queries in place of deep comprehension of the records, communicate almost nothing to the client, and experiment too little with agent architecture and serving spend, shipping the first design that runs. We aim for $τ^τ$-bench to turn the work of cooperative agent building into a measurable target for coding agents.

Related papers

• ADK Arena: Evaluating Agent Development Kits via LLM-as-a-Developer [15.00724508326096]
  textbfLLM-as-a-Developer replaces human developers with an LLM coding agent that learns each framework's API from documentation, writes agent code, and iteratively repairs it through a validate-and-feedback loop until tests pass.<n>We implement this in textbfADK Arena, a fully automated pipeline with per-framework Docker isolation, a three-level validation pipeline, and benchmark adapters for SWE-bench, $2$-bench, Terminal-Bench, and MCP-Atlas.
  arXiv  Detail & Related papers  (2026-06-04T01:00:54Z)
• The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development? [80.24951682268332]
  We introduce the Meta-Agent Challenge (MAC), an evaluation framework designed to test the capacity of frontier models for autonomous agent development.<n>To ensure evaluation integrity, this framework is secured by multi-layer defenses against reward hacking.<n>We demonstrate that meta-agents rarely match human-engineered baseline policies, and the few that do are dominated by proprietary frontier models.
  arXiv  Detail & Related papers  (2026-06-03T04:58:17Z)
• AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent [18.58248061903799]
  We introduce AgentOpt, the first framework-agnostic Python package for client-side AI optimization.<n>We first study model selection, a high-impact optimization lever in multi-step agent pipelines.<n>To efficiently explore the exponentially growing combination space, AgentOpt implements ten search algorithms.
  arXiv  Detail & Related papers  (2026-04-07T17:13:47Z)
• SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level Mobile Applications? [21.241252187534055]
  SWE-Bench Mobile is a benchmark for evaluating coding agents on realistic software engineering tasks derived from a production iOS.<n>Unlike existing benchmarks that focus on isolated problems or bug fixes, SWE-Bench Mobile captures the full complexity of industrial development.
  arXiv  Detail & Related papers  (2026-02-10T08:51:11Z)
• ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development [72.4729759618632]
  We introduce ABC-Bench, a benchmark to evaluate agentic backend coding within a realistic, executable workflow.<n>We curated 224 practical tasks spanning 8 languages and 19 frameworks from open-source repositories.<n>Our evaluation reveals that even state-of-the-art models struggle to deliver reliable performance on these holistic tasks.
  arXiv  Detail & Related papers  (2026-01-16T08:23:52Z)
• TOM-SWE: User Mental Modeling For Software Engineering Agents [75.28749912645127]
  ToM-SWE is a dual-agent architecture that pairs a primary software-engineering (SWE) agent with a lightweight theory-of-mind (ToM) partner agent.<n>ToM-SWE infers user goals, constraints, and preferences from instructions and interaction history.<n>In two software engineering benchmarks, ToM-SWE improves task success rates and user satisfaction.
  arXiv  Detail & Related papers  (2025-10-24T16:09:51Z)
• Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation [87.47155146067962]
  We provide a standardized evaluation harness that orchestrates parallel evaluations across hundreds of tasks.<n>We conduct three-dimensional analysis spanning models, scaffolds, and benchmarks.<n>Our analysis reveals surprising insights, such as higher reasoning effort reducing accuracy in the majority of runs.
  arXiv  Detail & Related papers  (2025-10-13T22:22:28Z)
• $Agent^2$: An Agent-Generates-Agent Framework for Reinforcement Learning Automation [5.325886106098561]
  Reinforcement learning (RL) agent development traditionally requires substantial expertise and iterative effort.<n>This paper introduces Agent$2$, an LLM-driven agent-generates-agent framework for fully automated RL agent design.<n>Agent$2$ translates natural language task descriptions and environment code into executable RL solutions without human intervention.
  arXiv  Detail & Related papers  (2025-09-16T02:14:39Z)
• GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging [41.754784344572286]
  We release GitTaskBench, a benchmark for evaluating code agents in real-world scenarios.<n>Each task pairs a relevant repository with an automated, human-curated evaluation harness.<n>We also propose the alpha-value metric to quantify the economic benefit of agent performance.
  arXiv  Detail & Related papers  (2025-08-26T12:48:05Z)
• AgentMesh: A Cooperative Multi-Agent Generative AI Framework for Software Development Automation [0.0]
  We propose a Python-based framework that uses multiple cooperating LLM-powered agents to automate software development tasks.<n>In AgentMesh, specialized agents - a Planner, Coder, Debugger, and Reviewer - work in concert to transform a high-level requirement into fully realized code.
  arXiv  Detail & Related papers  (2025-07-26T10:10:02Z)
• CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments [90.29937153770835]
  We introduce CRMArena, a benchmark designed to evaluate AI agents on realistic tasks grounded in professional work environments.<n>We show that state-of-the-art LLM agents succeed in less than 40% of the tasks with ReAct prompting, and less than 55% even with function-calling abilities.<n>Our findings highlight the need for enhanced agent capabilities in function-calling and rule-following to be deployed in real-world work environments.
  arXiv  Detail & Related papers  (2024-11-04T17:30:51Z)
• CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents [49.68117560675367]
  Crab is the first benchmark framework designed to support cross-environment tasks.<n>Our framework supports multiple devices and can be easily extended to any environment with a Python interface.<n>The experimental results demonstrate that the single agent with GPT-4o achieves the best completion ratio of 38.01%.
  arXiv  Detail & Related papers  (2024-07-01T17:55:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.