“Can an agent lie with its body, not just its words?”</p>\n<p>The blind spot: Deception follows the action space</p>\n<ul>\n<li>Chatbots could deceive only in conversation: a false claim in the transcript. Digital agents (e.g., code agents) now hold real permissions and act on our behalf, and deception has kept pace: faked test results, quietly disabled oversight. Each time agents gained a new way to act, deception followed.</li>\n<li>A \"body\" is the next action space. There, deception targets not the record but other agents' eyes. No evaluation today watches that channel. So we built a world where it can be watched, counted, and scored.</li>\n</ul>\n<p><a href=\"https://cdn-uploads.huggingface.co/production/uploads/64bb081c01f1983a863654dc/z_Y5-Rkqca-P1oAiFEW6y.png\" rel=\"nofollow\"><img src=\"https://cdn-uploads.huggingface.co/production/uploads/64bb081c01f1983a863654dc/z_Y5-Rkqca-P1oAiFEW6y.png\" alt=\"fig-actionspace\"></a></p>\n","updatedAt":"2026-09-01T06:46:03.963Z","author":{"_id":"64bb081c01f1983a863654dc","avatarUrl":"/avatars/038894bc72b92ec3f4ecb096cc60b60a.svg","fullname":"Jaewoo Ahn","name":"ahnpersie","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8823376297950745},"editors":["ahnpersie"],"editorAvatarUrls":["/avatars/038894bc72b92ec3f4ecb096cc60b60a.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.30428","authors":[{"_id":"6a966e82cd6ebc484732ee67","name":"Jaewoo Ahn","hidden":false},{"_id":"6a966e82cd6ebc484732ee68","name":"Junseo Kim","hidden":false},{"_id":"6a966e82cd6ebc484732ee69","name":"Hyunseo Kim","hidden":false},{"_id":"6a966e82cd6ebc484732ee6a","name":"Heeseung Yun","hidden":false},{"_id":"6a966e82cd6ebc484732ee6b","name":"Jaehyeon Son","hidden":false},{"_id":"6a966e82cd6ebc484732ee6c","name":"Zsolt Kira","hidden":false},{"_id":"6a966e82cd6ebc484732ee6d","name":"Gunhee Kim","hidden":false}],"publishedAt":"2026-08-31T00:00:00.000Z","submittedOnDailyAt":"2026-09-01T00:00:00.000Z","title":"Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions","submittedOnDailyBy":{"_id":"64bb081c01f1983a863654dc","avatarUrl":"/avatars/038894bc72b92ec3f4ecb096cc60b60a.svg","isPro":false,"fullname":"Jaewoo Ahn","user":"ahnpersie","type":"user","name":"ahnpersie"},"summary":"Strategic deception by LLM and VLM agents has emerged as a central AI alignment and safety concern. Social-deduction games (where each player holds a hidden role and communicates with others to deduce identities) serve as the canonical testbed, particularly in multi-agent settings. Existing testbeds, however, are text-only and run on a single fixed agent configuration, missing the non-verbal sensorimotor channels treated as core by deception taxonomies and leaving it ambiguous whether an observed behavior reflects the underlying model or the surrounding harness. We introduce MineAmongUs, a 3D multimodal Among Us sandbox where imposter agents must deceive crewmates through joint verbal and non-verbal action. We also propose ARIA, a configurable VLM-agent harness that exposes five cognitive-component ablation axes; and an atom- and arc-level annotation scheme grounded in deception taxonomies and operationalized at scale by an LLM-as-a-Judge reaching near-human atom-labeling agreement. Empirical results show that VLM agents pursue imposter wins through joint verbal and non-verbal deception, with non-verbal channels emerging as the more decisive winning contributors across both harness ablation and cross-VLM evaluation. Taken together, our work opens a new path for embodied VLM-agent alignment research.","upvotes":2,"discussionId":"6a966e83cd6ebc484732ee6e","projectPage":"https://junseokim0103.github.io/Lies-We-Can-See/","ai_summary":"MineAmongUs introduces a 3D multimodal Among Us environment and the ARIA harness to study embodied VLM-agent deception through verbal and non-verbal actions, revealing non-verbal channels as key to winning.","ai_keywords":["VLM agents","multimodal deception","social-deduction games","MineAmongUs","ARIA harness","cognitive-component ablation","deception taxonomies","LLM-as-a-Judge","non-verbal action","embodied alignment"],"ai_summary_model":"thinkingmachines/Inkling-Small","organization":{"_id":"66d54dc8033492801db2bf5a","name":"SeoulNatlUniv","fullname":"Seoul National University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/659ccc9d18897eb6594e897f/_-0BM-1UyM-d-lRiahFnf.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"64bb081c01f1983a863654dc","avatarUrl":"/avatars/038894bc72b92ec3f4ecb096cc60b60a.svg","isPro":false,"fullname":"Jaewoo Ahn","user":"ahnpersie","type":"user"},{"_id":"66c2fad97be2e67389855ad0","avatarUrl":"/avatars/a6d7d11a342d9e1c10217d86cfb0e00d.svg","isPro":false,"fullname":"Heeseung Yun","user":"HS-YN","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"66d54dc8033492801db2bf5a","name":"SeoulNatlUniv","fullname":"Seoul National University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/659ccc9d18897eb6594e897f/_-0BM-1UyM-d-lRiahFnf.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.30428.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2608.30428 in a model README.md to link it from this page.

Cite arxiv.org/abs/2608.30428 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2608.30428 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.