Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.16456 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911602922487808 |
|---|---|
| author | Modi, Smit Nautambhai Mahajan, Gandharv Wetter, Marc Welles, Randall |
| author_facet | Modi, Smit Nautambhai Mahajan, Gandharv Wetter, Marc Welles, Randall |
| contents | Real-time voice assistants must revise task state when users interrupt mid-response, but existing spoken-dialog benchmarks largely evaluate turn-based interaction and miss this failure mode. We introduce EchoChain, a controlled benchmark for evaluating full-duplex state-update reasoning under mid-speech interruptions. EchoChain identifies three recurring failure patterns in post-interruption continuations: contextual inertia, interruption amnesia, and objective displacement. The benchmark generates scenario-driven conversations and injects interruptions at a standardized point relative to assistant speech onset, enabling controlled cross-model comparison. In a paired half-duplex control, total failures drop by 40.2% relative to interrupted runs, indicating that many errors are driven by state-update reasoning under interruption rather than task difficulty alone. Across evaluated real-time voice models, no system exceeds a 50% pass rate, showing substantial room for improvement in mid-generation state revision. EchoChain provides a reproducible benchmark for diagnosing state-update reasoning failures in full-duplex voice interaction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_16456 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EchoChain: A Full-Duplex Benchmark for State-Update Reasoning Under Interruptions Modi, Smit Nautambhai Mahajan, Gandharv Wetter, Marc Welles, Randall Computation and Language Artificial Intelligence Machine Learning Sound Real-time voice assistants must revise task state when users interrupt mid-response, but existing spoken-dialog benchmarks largely evaluate turn-based interaction and miss this failure mode. We introduce EchoChain, a controlled benchmark for evaluating full-duplex state-update reasoning under mid-speech interruptions. EchoChain identifies three recurring failure patterns in post-interruption continuations: contextual inertia, interruption amnesia, and objective displacement. The benchmark generates scenario-driven conversations and injects interruptions at a standardized point relative to assistant speech onset, enabling controlled cross-model comparison. In a paired half-duplex control, total failures drop by 40.2% relative to interrupted runs, indicating that many errors are driven by state-update reasoning under interruption rather than task difficulty alone. Across evaluated real-time voice models, no system exceeds a 50% pass rate, showing substantial room for improvement in mid-generation state revision. EchoChain provides a reproducible benchmark for diagnosing state-update reasoning failures in full-duplex voice interaction. |
| title | EchoChain: A Full-Duplex Benchmark for State-Update Reasoning Under Interruptions |
| topic | Computation and Language Artificial Intelligence Machine Learning Sound |
| url | https://arxiv.org/abs/2604.16456 |