An Interactive Agent for Requirement-Driven Candidate Sourcing
2026-08-24 • Software Engineering
Software Engineering
AI summaryⓘ
The authors look at the problem of finding people based on vague natural language descriptions, like "ML engineers moving into biotech research." They argue that this is not just about searching, but about understanding and refining the requirement first. They introduce a system called \sys]0m\ that interacts with the user to clarify and validate the request before searching, improving the quality of results. They also present a benchmark, \bench]0m\, to evaluate such systems. Their system finds a broader and more relevant set of candidates than many existing methods, showing that careful requirement handling is key to better people sourcing.
requirements engineeringnatural language processingcandidate sourcinglarge language modelsinformation retrievalvalidationverificationbenchmarkinginteractive systemspeople search
Authors
Yuanpeng He, Fangjing Li, Xiangyu Ru, Kexin Sun, Kun Yang, Lijian Li, Chi-Man Pun, Qingsong Wen, Wenpin Jiao, Mingkai Guo, Yirong Feng, Daiheng Gao, Zhi Jin
Abstract
Finding people from a natural-language description (``ML engineers transitioning to research roles in biotech'') is increasingly delegated to LLM agents and framed as information retrieval. We argue that it is fundamentally a requirements engineering task: such a request is an under-determined requirement with implicit constraints, many valid answers, and no acceptance criterion, so useful answers require eliciting, validating, and verifying the requirement before search can matter. We present \sys{}, to our knowledge the first interactive, requirements-driven candidate-sourcing agent (it elicits, validates, retrieves, and verifies a vague people-request into a justified slate through bounded elicitation, workflow templates, a two-stage commit protocol, and bidirectional termination guards) and \bench{}, a benchmark that runs the requirements lifecycle (criteria-anchored validation, multi-model evidence-grounded oracle construction, and cost-aware verification). Across $21$ systems and all $691$ requirements, \sys{} dominates breadth ($100%$ coverage at $2.5\times$ the yield) and is \emph{near-orthogonal} to the field, with $90%$ of the people it returns are surfaced by \emph{none} of $20$ strong LLM-plus-web baselines combined. Beyond breadth, an evidence-grounded judging of every system shows \sys{} \emph{recalls} the most relevant real people: $0.241$ of the union pool, $1.9\times$ the next system, with a bootstrap $95%$ interval disjoint from every baseline. \sys{} is thus the strongest \emph{sourcing} engine (the deepest real, reachable candidate pool), while precision-ranking LLMs serve as~complementary verifiers.