{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:59:11Z","timestamp":1773806351436,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"39","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Critical thinking is essential for building robust AI systems, preventing them from blindly accepting flawed data or biased reasoning.\nHowever, prior work has primarily focused on passive critical thinking, where models simply reject problematic queries without taking constructive steps to address user requests.\nIn this work, we introduce proactive critical thinking, a paradigm where models actively seek missing or clarifying information from users to resolve their queries better.\nTo evaluate this capability, we present GSM-MC and GSM-MCE, two novel benchmarks based on GSM8K for assessing mathematical reasoning under incomplete or misleading conditions.\nExperiments on Qwen3 and Llama series models show that, while these models excel in traditional reasoning tasks, they struggle with proactive critical thinking, especially smaller ones.\nHowever, we demonstrate that reinforcement learning (RL) can significantly improve this ability. By incorporating heuristic information into the reward function, we achieve substantial gains, boosting the Qwen3-1.7B's accuracy from 0.15% to 73.98% on GSM-MC.\nWe hope this work advances models that collaborate more effectively with users in problem-solving through proactive critical thinking.<\/jats:p>","DOI":"10.1609\/aaai.v40i39.40621","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:59:06Z","timestamp":1773802746000},"page":"33350-33358","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Passive Critical Thinking: Fostering Proactive Questioning to Enhance Human-AI Collaboration"],"prefix":"10.1609","volume":"40","author":[{"given":"Ante","family":"Wang","sequence":"first","affiliation":[]},{"given":"Yujie","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Jingyao","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Suhang","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xinyan","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Jinsong","family":"Su","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40621\/44582","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40621\/44582","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:59:06Z","timestamp":1773802746000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/40621"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"39","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i39.40621","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}