Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.08682 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918286166327296 |
|---|---|
| author | Chawla, Kushal Zhu, Chenyang Cai, Pengshan Cho, Sangwoo Novotney, Scott Singh, Ayushman Lewis, Jonah Safewright, Keasha Samuel, Alfy Babinsky, Erin Zhang, Shi-Xiong Sahu, Sambit |
| author_facet | Chawla, Kushal Zhu, Chenyang Cai, Pengshan Cho, Sangwoo Novotney, Scott Singh, Ayushman Lewis, Jonah Safewright, Keasha Samuel, Alfy Babinsky, Erin Zhang, Shi-Xiong Sahu, Sambit |
| contents | Summarization of multi-party dialogues is a critical capability in industry, enhancing knowledge transfer and operational effectiveness across many domains. However, automatically generating high-quality summaries is challenging, as the ideal summary must satisfy a set of complex, multi-faceted requirements. While summarization has received immense attention in research, prior work has primarily utilized static datasets and benchmarks, a condition rare in practical scenarios where requirements inevitably evolve. In this work, we present an industry case study on developing an agentic system to summarize multi-party interactions. We share practical insights spanning the full development lifecycle to guide practitioners in building reliable, adaptable summarization systems, as well as to inform future research, covering: 1) robust methods for evaluation despite evolving requirements and task subjectivity, 2) component-wise optimization enabled by the task decomposition inherent in an agentic architecture, 3) the impact of upstream data bottlenecks, and 4) the realities of vendor lock-in due to the poor transferability of LLM prompts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_08682 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Lessons from the Field: An Adaptable Lifecycle Approach to Applied Dialogue Summarization Chawla, Kushal Zhu, Chenyang Cai, Pengshan Cho, Sangwoo Novotney, Scott Singh, Ayushman Lewis, Jonah Safewright, Keasha Samuel, Alfy Babinsky, Erin Zhang, Shi-Xiong Sahu, Sambit Computation and Language Artificial Intelligence Summarization of multi-party dialogues is a critical capability in industry, enhancing knowledge transfer and operational effectiveness across many domains. However, automatically generating high-quality summaries is challenging, as the ideal summary must satisfy a set of complex, multi-faceted requirements. While summarization has received immense attention in research, prior work has primarily utilized static datasets and benchmarks, a condition rare in practical scenarios where requirements inevitably evolve. In this work, we present an industry case study on developing an agentic system to summarize multi-party interactions. We share practical insights spanning the full development lifecycle to guide practitioners in building reliable, adaptable summarization systems, as well as to inform future research, covering: 1) robust methods for evaluation despite evolving requirements and task subjectivity, 2) component-wise optimization enabled by the task decomposition inherent in an agentic architecture, 3) the impact of upstream data bottlenecks, and 4) the realities of vendor lock-in due to the poor transferability of LLM prompts. |
| title | Lessons from the Field: An Adaptable Lifecycle Approach to Applied Dialogue Summarization |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.08682 |