Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions

arXiv:2608.30428 · cs.CL, cs.AI, cs.CV, cs.LG · Submitted 2026-08-31 · Read on arXiv

cs.CL, cs.AI, cs.CV, cs.LG

Submitted: 2026-08-31

Updated: 2026-08-31

Comments: Workshop on Agent Behavior (WAB) at COLM 2026. Project page: https://junseokim0103.github.io/Lies-We-Can-See/

Code: https://github.com/prismarinejs/mineflayer

Project page: https://junseokim0103.github.io/Lies-We-Can-See

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Ablation — 22× in this paper · explained in 1 episode
• Benchmark — 17× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 10× in this paper · explained in 3 episodes
• Alignment — 7× in this paper · explained in 1 episode
• Archetype — 7× in this paper · explained in 1 episode
• Robustness — 7× in this paper · explained in 5 episodes
• Adaptation — 6× in this paper · explained in 1 episode
• Action Space — 5× in this paper · explained in 1 episode
• Actor — 5× in this paper · explained in 3 episodes
• Agent Harness — 5× in this paper · explained in 2 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Core — 4× in this paper · explained in 2 episodes
• LLM judge — 4× in this paper · explained in 2 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Annotator Agreement — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Cooperation — 2× in this paper · explained in 2 episodes
• Embodied AI — 2× in this paper · explained in 2 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Interpersonal Deception Theory — 2× in this paper
• Multi-Agent System — 2× in this paper · explained in 6 episodes
• Opportunity Patience — 2× in this paper
• Trace — 2× in this paper · explained in 2 episodes
• AI Alignment — 1× in this paper · explained in 2 episodes
• Abstention — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Agent Interactions — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Chain-of-Thought (CoT) Reasoning — 1× in this paper · explained in 2 episodes
• Deferral — 1× in this paper · explained in 2 episodes
• External Validation — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Linear probe — 1× in this paper · explained in 2 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 9 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Standardized Benchmarks — 1× in this paper · explained in 2 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• AMONGAGENTS: Evaluating Large Language Models in the Interactive Text-Based Social Deduction Game
• The Traitors: Deception and Trust in Multi-Agent Language Model Simulations
• AI2-THOR: An Interactive 3D Environment for Visual AI
• Meta-Harness: End-to-End Optimization of Model Harnesses
• TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft
• Frontier Models are Capable of In-context Scheming
• Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models
• The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems
• CONSCIENTIA: Can LLM Agents Learn to Strategize? Emergent Deception and Trust in a Multi-Agent NYC Simulation
• Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation
• Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf
• MineLand: Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs
• VideoGameBench: Can Vision-Language Models complete popular video games?

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering