Abstract:We demonstrate LLARS (LLM Assisted Research System), an open-source platform that bridges the gap between domain experts and developers for building LLM-based systems. It integrates three tightly connected modules into an end-to-end pipeline: Collaborative Prompt Engineering for real-time co-authoring with version control and instant LLM testing, Batch Generation for configurable output production across user-selected prompts $\times$ models $\times$ data with cost control, and Hybrid Evaluation where human and LLM evaluators jointly assess outputs through diverse assessment methods, with live agreement metrics and provenance analysis to identify the best model-prompt combination for a given use case. New prompts and models are automatically available for batch generation and completed batches can be turned into evaluation scenarios with a single click. Interviews with six domain experts and three developers in online counselling confirmed that LLARS feels intuitive, saves considerable time by keeping everything in one place and makes interdisciplinary collaboration seamless.
| Comments: | Accepted at IJCAI-ECAI 2026 Demonstrations Track. Demo video: this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC); Software Engineering (cs.SE) |
| Cite as: | arXiv:2605.10593 [cs.AI] |
| (or arXiv:2605.10593v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.10593 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Philipp Steigerwald [view email]
[v1]
Mon, 11 May 2026 14:00:27 UTC (319 KB)