arXiv AI
Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 31
Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems
arXiv:2607. 26120v1 Announce Type: new Abstract: Large Language Models (LLMs)-powered multi-agent systems are increasingly deployed in mixed-motive environments, where agents operate under asymmetric information and strategic deception due to conflicting or hidden objectives.
arXiv AI
Jul 3
Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence
arXiv:2604. 08169v2 Announce Type: replace Abstract: Alignment in LLMs is more brittle than commonly assumed: misalignment can be induced by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization.
arXiv AI
Aug 11
Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games
arXiv:2604. 11741v2 Announce Type: replace Abstract: Vision-language models (VLMs) have shown impressive capabilities in perceptual tasks, yet they degrade in complex multi-hop reasoning under multiplayer game settings with imperfect and deceptive information.
arXiv AI
Sep 1
QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents
arXiv:2605.27068v2 Announce Type: replace-cross Abstract: Social deduction games have become a popular testbed for probing reasoning, deception, coordination, and belief modeling in Large Language Mo...
arXiv AI
Oct 23
Fig: Automated Multiagent Behavior Elicitor
Fig (Finding Interactions in Games) is an agentic system that performs targeted elicitation interventions on game environments to study multiagent behaviors. It takes a natural‑language behavior description, decomposes it into sub‑behaviors, generates or selects appropriate social games, and applies interventions to the game engine, opponents, instructions, and context. The system evaluates model behavior using mechanical checks and synthetic rubric judgments, and human review validates the interventions, generated games, and evaluation mechanisms. In experiments, models attempted the target behavior in 45.2% of episodes on average for six test behaviors, and Fig’s interventions increased attempt rates by 10.9% compared to matched control games.
arXiv AI
Jun 2
SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence
arXiv:2606. 02380v1 Announce Type: cross Abstract: As LLM-based agents expand their operational scope, reliability becomes a prerequisite for real-world deployment.