Routesplain: Towards Faithful and Intervenable Routing for Software-related Tasks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911261939204096 |
|---|---|
| author | Štorek, Adam Upadhyay, Vikas Liu, Marianne Menglin Peterson, Daniel W. Mittal, Anshul Bharadwaj, Sujeeth Shah, Fahad Roth, Dan |
| author_facet | Štorek, Adam Upadhyay, Vikas Liu, Marianne Menglin Peterson, Daniel W. Mittal, Anshul Bharadwaj, Sujeeth Shah, Fahad Roth, Dan |
| contents | LLMs now tackle a wide range of software-related tasks, yet we show that their performance varies markedly both across and within these tasks. Routing user queries to the appropriate LLMs can therefore help improve response quality while reducing cost. Prior work, however, has focused mainly on general-purpose LLM routing via black-box models. We introduce Routesplain, the first LLM router for software-related tasks, including multilingual code generation and repair, input/output prediction, and computer science QA. Unlike existing routing approaches, Routesplain first extracts human-interpretable concepts from each query (e.g., task, domain, reasoning complexity) and only routes based on these concepts, thereby providing intelligible, faithful rationales. We evaluate Routesplain on 16 state-of-the-art LLMs across eight software-related tasks; Routesplain outperforms individual models both in terms of accuracy and cost, and equals or surpasses all black-box baselines, with concept-level intervention highlighting avenues for further router improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_09373 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Routesplain: Towards Faithful and Intervenable Routing for Software-related Tasks Štorek, Adam Upadhyay, Vikas Liu, Marianne Menglin Peterson, Daniel W. Mittal, Anshul Bharadwaj, Sujeeth Shah, Fahad Roth, Dan Software Engineering Computation and Language Machine Learning LLMs now tackle a wide range of software-related tasks, yet we show that their performance varies markedly both across and within these tasks. Routing user queries to the appropriate LLMs can therefore help improve response quality while reducing cost. Prior work, however, has focused mainly on general-purpose LLM routing via black-box models. We introduce Routesplain, the first LLM router for software-related tasks, including multilingual code generation and repair, input/output prediction, and computer science QA. Unlike existing routing approaches, Routesplain first extracts human-interpretable concepts from each query (e.g., task, domain, reasoning complexity) and only routes based on these concepts, thereby providing intelligible, faithful rationales. We evaluate Routesplain on 16 state-of-the-art LLMs across eight software-related tasks; Routesplain outperforms individual models both in terms of accuracy and cost, and equals or surpasses all black-box baselines, with concept-level intervention highlighting avenues for further router improvements. |
| title | Routesplain: Towards Faithful and Intervenable Routing for Software-related Tasks |
| topic | Software Engineering Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2511.09373 |