$τ^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909643971756032 |
|---|---|
| author | Barres, Victor Dong, Honghua Ray, Soham Si, Xujie Narasimhan, Karthik |
| author_facet | Barres, Victor Dong, Honghua Ray, Soham Si, Xujie Narasimhan, Karthik |
| contents | Existing benchmarks for conversational AI agents simulate single-control environments, where only the AI agent can use tools to interact with the world, while the user remains a passive information provider. This differs from real-world scenarios like technical support, where users need to actively participate in modifying the state of the (shared) world. In order to address this gap, we introduce $τ^2$-bench, with four key contributions:
1) A novel Telecom dual-control domain modeled as a Dec-POMDP, where both agent and user make use of tools to act in a shared, dynamic environment that tests both agent coordination and communication,
2) A compositional task generator that programmatically creates diverse, verifiable tasks from atomic components, ensuring domain coverage and controlled complexity,
3) A reliable user simulator tightly coupled with the environment, whose behavior is constrained by tools and observable states, improving simulation fidelity,
4) Fine-grained analysis of agent performance through multiple ablations including separating errors arising from reasoning vs communication/coordination.
In particular, our experiments show significant performance drops when agents shift from no-user to dual-control, highlighting the challenges of guiding users. Overall, $τ^2$-bench provides a controlled testbed for agents that must both reason effectively and guide user actions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_07982 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | $τ^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment Barres, Victor Dong, Honghua Ray, Soham Si, Xujie Narasimhan, Karthik Artificial Intelligence Computation and Language Existing benchmarks for conversational AI agents simulate single-control environments, where only the AI agent can use tools to interact with the world, while the user remains a passive information provider. This differs from real-world scenarios like technical support, where users need to actively participate in modifying the state of the (shared) world. In order to address this gap, we introduce $τ^2$-bench, with four key contributions: 1) A novel Telecom dual-control domain modeled as a Dec-POMDP, where both agent and user make use of tools to act in a shared, dynamic environment that tests both agent coordination and communication, 2) A compositional task generator that programmatically creates diverse, verifiable tasks from atomic components, ensuring domain coverage and controlled complexity, 3) A reliable user simulator tightly coupled with the environment, whose behavior is constrained by tools and observable states, improving simulation fidelity, 4) Fine-grained analysis of agent performance through multiple ablations including separating errors arising from reasoning vs communication/coordination. In particular, our experiments show significant performance drops when agents shift from no-user to dual-control, highlighting the challenges of guiding users. Overall, $τ^2$-bench provides a controlled testbed for agents that must both reason effectively and guide user actions. |
| title | $τ^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2506.07982 |