Knowing When to Ask: Self-Gated Clarification for Hierarchical Language Agents

Computer Science > Artificial Intelligence [Submitted on 9 Jun 2026] Knowing When to Ask: Self-Gated Clarification for Hierarchical Language Agents Aijing Gao, Yiming Kang, Mengdie Flora Wang, Jae Oh Woo In hierarchical reasoning, failures often originate at intermediate decision points where the agent commits to a wrong branch without recognizing that it lacks critical information. Rather than treating clarification as an external uncertainty trigger, we propose ACTION-RATING, a formulation that places it inside the agent's action space on a shared ordinal scale with navigation, so that asking competes directly with acting at every decision point and help-seeking becomes observable at intermediate states. Two structurally distinct information-seeking modes emerge from the agent's own ratings: mandatory (no viable branch) and opportunistic (residual uncertainty despite a leading candidate). On Harmonized Tariff Schedule classification (30,000-node taxonomy, three benchmarks, 9~LLMs across 4 families), we observe a regime shift from mandatory to opportunistic clarification, with Information-Seeking Effectiveness (ISE), a local diagnostic defined as the fraction of help interactions followed by a correct next navigation step (not a final-task metric), rising from 50% to 74%. Three diagnostic contrasts fail to reproduce this structure. A separability test shows that the information-seeking pattern (mode split, ISE ranking) persists when answer quality is degraded (-18.8% accuracy), supporting an empirical separation between where an agent seeks help and the quality of the help it receives. Under the controlled answer channel, accuracy gains reach +16.2% at 10-digit; we read this as an upper bound on what better localization could unlock, not a deployment estimate. Subjects: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) Cite as: arXiv:2606.11349 [cs.AI]   (or arXiv:2606.11349v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.11349 Focus to learn more Submission history From: Aijing Gao [view email] [v1] Tue, 9 Jun 2026 18:25:57 UTC (567 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.HC References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)