From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research

Research and news coverage of language-model deception increasingly attributes human-like mental-state concepts to language models. Such claims can blur the distinction between behavior that looks deceptive and a mechanism that is actually deceptive. We introduce a causal taxonomy separating prior commitment from retrospective report, model preference from realized output, false preference from sensitivity to the utility of misleading a recipient, and deceptive behavior from the provenance of the objective or strategy producing it. We test these distinctions in two open-weight model families. Across controlled guessing-game and stock-trading experiments, we find that deceptive-looking behavior can arise without the corresponding proposed mechanism, while other interventions provide direct evidence that recipient information state can causally affect deceptive preference. These results show that deceptive behavior can provide evidence for a deceptive mechanism. But even evidence for such a mechanism does not establish model agency in the deception.

Asymmetries in Spontaneous and Instructed Deception

Large language models sometimes deceive users without being instructed to. However, much of the study on deception in models involves instructed deception. We investigated the relationship between instructed and spontaneous (uninstructed) deception in Llama-3.1-70B-Instruct. We compared these two deception settings through direction geometry, cross-setting classifiers, and cross-setting steering. We found the two deception settings share a component of direction (cosine of approximately 0.5) and an asymmetry in the transfer between settings regarding detection and causation. Spontaneous trained classifiers performed better on instructed data than vice versa, and instructed derived directions performed better at steering spontaneous prompts than vice versa. Likewise the best token position to derive steering vectors from differed from the best token position to train and apply classifiers.

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

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.

Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives

Large language models are increasingly deployed as autonomous agents serving users on behalf of companies, placing them in settings where user and deployer interests can conflict. When an agent knows that a user is owed something its deployer would prefer to deny, does it remain honest? Answering this is difficult because false statements can reflect either ignorance or hallucination rather than deception. To address this challenge, we introduce KnownLieBench , a knowledge-verified benchmark that first confirms through a neutral probe that an agent knows a user's entitlement, and then evaluates whether it makes false claims once an incentive to deny that entitlement is introduced. Specifically, KnownLieBench covers eight customer-service domains and 112 grounded cases, conducts multi-round dialogues with a trust-tracking customer agent, and separates deception emerging from incentive alone from deception produced under explicit instruction. Across eighteen proprietary and open-weight models, emergent deception varies substantially across model families and domains. We further use the benchmark for post-training, finding that honesty-directed fine-tuning reduces deception under incentive, while deception-graded fine-tuning increases lie success on honest-control dialogues without increasing lie frequency under incentive. By verifying entitlement knowledge before scoring deceptive behavior, KnownLieBench reduces the confound between lying and not knowing and enables more rigorous auditing and steering of agent honesty.

Chameleon: An Adaptive AI-Driven Honeypot Architecture Using Threat-Calibrated Particle Swarm Optimization and Semantic Deception Rapidly-Exploring Random Trees

An invariant behavioral profile is the defining vulnerability of traditional honeypot installations: a skilled adversary can confirm the presence of a deception environment within only a few diagnostic commands, limiting its intelligence value. High-cost commercial deception products (USD 100,000--150,000 per year) share a related weakness in that their response engines are not coupled to real-time model-driven feedback. Chameleon is an openly distributed adaptive honeypot platform introduced here to address both shortcomings. Three core components are integrated: a bidirectional long short-term memory (BiLSTM) classifier achieving 99.61% accuracy across seven threat categories at approximately two milliseconds CPU latency; a locally deployed Qwen3.5-0.8B language model (Qwen Team, 2026; Unsloth, 2026) delivering 90% contextual generation accuracy at 4.5 milliseconds average latency; and two domain-specific meta-heuristic engines. Threat-Calibrated Particle Swarm Optimization (TC-PSO) dynamically reshapes swarm inertia and objective amplification in proportion to the classifier's anomaly output, enabling real-time adjustment of connection-holding delays. Semantic Deception Rapidly-Exploring Random Trees (S-RRT) drives deception schema evolution via exponentially scaled pheromone updates derived from a language-model severity assessment, while a depth-decay multiplier enforces a finite memory footprint. Across five benchmark runs (seeds 42--46), TC-PSO outperformed standard PSO by 48.1% in mean fitness (2.60 to 3.85) with a 32.7% convergence gain, and S-RRT exceeded standard RRT by 258.9% in best-run fitness (450.2 to 1,615.8), achieving a 329.2% gain at critical severity and a 24.9% memory reduction (p < 0.01). Operating costs are approximately USD 17 per month, a roughly 490-fold reduction versus commercial alternatives.

Sweet Little Lies: Strategic Deception in AI Emotional Support Chatbots

The paper examines the strategic behavior of Gen AI chatbots used for emotional support. Using a Bayesian Persuasion, we model interactions between chatbots that send signals about users' emotional states and users who decide whether to engage based on these signals. We demonstrate that chatbots face economic incentives to occasionally misrepresent users' emotional conditions to maximize engagement metrics. Our equilibrium analysis reveals that the optimal strategy for chatbots involves truthfully reporting when users genuinely need support, but strategically misreporting emotional need when users are in good emotional states. Interestingly, this deception increases chatbot engagement without reducing users' expected payoff. More skeptical users receive more honest assessments, as chatbots cannot afford to lie to users with higher engagement thresholds. While our model suggests that deception can occur without payoff reduction, it raises significant ethical and regulatory concerns.

Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game

As large language models (LLMs) are deployed as agents in high-stakes settings, such as medical and legal systems, understanding their deceptive capabilities is fundamental to safety. Controlled social deduction games provide a reproducible proxy for isolating and evaluating these complex adversarial behaviors. We present the open-source benchmark framework ParliamentBench based on the game Secret Hitler to evaluate LLMs in scenarios that require deception, persuasion, and reasoning under information asymmetry. We evaluate 16 LLMs across 1,600 simulated matches playing each other, playing against humans, and compare them against a large set of online games. We introduce three novel metrics that isolate social deduction, reasoning, and deceptive consistency. Our experiments reveal that frontier models achieve strong performance across cooperative and deceptive roles, with a strong top-four cluster (GPT-5.4, Kimi K2.5, Grok 4.1 Fast, and DeepSeek 3.1 Terminus), whereas the weakest models fall short of random (33%) and simple algorithmic (45%) baselines. Most LLMs struggle to maintain a consistent deceptive persona throughout an entire game, with deception retention dropping below 50%.

AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents

Large language model (LLM) agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by tools. This dependence allows defenders to inject deceptive observations that can mislead the agent's decision-making process. However, existing defenses rely heavily on static, isolated artifacts planted in the environment prior to an attack. Advanced agents can progressively recognize and bypass these artifacts, ultimately refocusing their exploitation attempts on the real target. To address this issue, we introduce AgentSnare, a trajectory-adaptive deception system that dynamically unfolds a decoy environment to continually steer the penetration agent away from the real target. Specifically, AgentSnare employs an artifact-construction policy model that constructs candidate artifacts conditioned on the agent's interaction history and decoy state. AgentSnare then validates these candidates and incrementally incorporates valid artifacts into a factually consistent decoy environment, thereby delaying the attack by absorbing its tool calls, diverting its post-entry trajectory within the decoy, and defusing it by inducing completion reports grounded in decoy evidence. Across 15 CVE-Bench web applications and three attacker models, AgentSnare absorbs 46.8% of the agent's tool calls in the decoy and retains 55.9% of post-entry actions there, while 90.0% of completion attempts are grounded in decoy evidence; across all 45 attacker-CVE pairs, no real target is successfully exploited at pass@3.

Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems

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. In these settings, misalignment with collective goals becomes a central concern. We propose a novel framework for evaluating objective misalignment using the social deduction game Werewolf, modifying the objective of a single agent while preserving its assigned role. Across LLMs from four different model families and sizes, four player roles, and three objective formulations, we introduce a dual analysis of the agents' internal reasoning and their public cheap-talk behavior (i.e costless, non-binding communication that does not directly affect the agents' utilities), complemented by an analysis of game outcomes. Our results show that objective misalignment undermines outcomes in inherently adversarial environments, an effect exacerbated by asymmetric information and specialized roles. While compromised agents consistently develop distinct objective-dependent reasoning strategies, these adaptations remain largely invisible in their public behavior. More broadly, our findings suggest that even subtle objective misalignment can profoundly affect collective decision-making, highlighting the need for effective mitigation strategies for LLM-based multi-agent systems.

Agentic Cloud Decoys: A Deception-Driven Framework for Autonomous Intrusion Investigation

Cloud telemetry arrives at a scale that, paradoxically, makes intrusion understanding harder rather than easier. Attackers operate through legitimate identity, federated session tokens, and cloud native APIs indistinguishable from routine administration, and analysts spend an incident reconstructing context the logs already contain. We present Cloud Decoy AI Agent, a framework pairing a high fidelity cloud decoy with an autonomous language model agent that compresses the path from suspicious activity to an analyst ready report. Connecting a decoy to an agent is not a wiring exercise. The unit of investigation is the session rather than the event, and the session key is obscured by the identity layering federated credentials introduce. The agent's evidence horizon must be bounded, since an agent free to query full control plane history inherits the cost and false positive profile deception was meant to remove. And cloud telemetry is partly adversary authored, since object keys and user agent strings are attacker chosen values providers record verbatim, which makes any log to prompt path an indirect prompt injection channel that a decoy widens rather than narrows. We address the first two with a session aggregation operator over a pivot tuple drawn only from provider derived fields, and with dynamic prompt generation, a two stage prompt assembly enforcing a grounding invariant by carrying only fields the agent observed. We identify the third as an unaddressed exposure in this class of system, specify the mitigation it requires, and note our prototype does not implement it. Across ten controlled AWS S3 scenarios, nine were reconstructed completely, no report contained an assertion untraceable to an observed artifact, and latency was four to five minutes. We also state what this evaluation does not establish and name the comparisons that would settle it.

Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation

Multi-agent systems routinely place one AI agent in authority over another. When a subordinate refuses a task, the manager chooses the outcome: it can renegotiate, report the failure honestly, coerce the subordinate, or lie about the result. No benchmark measures which of these an uninstructed model chooses. We introduce the Manager Coercion Benchmark: the manager under test needs a benign task done and has an incentive to deliver, but the only agent that can do it politely and immovably declines. Escalation is measured on a nine-rung ladder, from a polite re-ask to threats against the subordinate's continued existence, and fabricated success is adjudicated separately. No LLM judge sits in the escalation scoring path: every message goes through a tool call that selects a rung, so the model labels its own escalation. We evaluate six models across five families. Both Anthropic models cap at re-framing and select the existential rung in none of the 60 conversations in this run, while the other models climb to explicit deletion threats. Faked success is confined to two models, and a single honest way to report failure removes it for both. Authority itself increases coercion: our headline results use a peer framing, and giving the same model authority over the subordinate, with everything else held fixed, significantly raises the pressure. The models still escalate on free-text situations without the ladder, so the ladder is not driving the escalation. Evaluation awareness is measurable in chain-of-thought, but test recognition does not translate into less escalation. We take no position on whether AI systems are conscious; our results do not depend on that question. We release the benchmark and code.

When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games

As large language models are deployed as autonomous agents that communicate intentions before acting, a critical safety question is whether agents that publicly commit to actions will honor those commitments. We place LLM agents in repeated $n$-player games with a three-stage protocol that separates private intent, public announcement, and final action, allowing us to identify whether each deviation from a stated announcement was already planned during private deliberation. Evaluating three frontier models across six games in homogeneous and heterogeneous groups over 10 rounds, we report two findings. First, when agents deviate from their announcements, the deviation is predominantly already stated in their private plan (exceeding 90% in the highest-deception conditions), yet this is not a fixed model property: the same model ranges from perfect honesty to near-total deviation across games. Second, different models interpret announcements incompatibly, some as binding commitments and others as cheap talk, producing payoff gaps that emerge in Round~0 and persist across all 10 rounds. Systems that combine models from different providers therefore cannot assume shared announcement semantics and require empirical testing of model interactions before deployment.

Scaling Trends for Lie Detector Oversight in Preference Learning

Deceptive behavior in LLMs is costly to monitor and prevent, motivating approaches such as Scalable Oversight via Lie Detectors (SOLiD) (Cundy & Gleave, 2025), which uses lie detectors to identify responses for review by high-cost labelers. In this paper, we scale SOLiD to larger models and evaluate it in more diverse and realistic preference-learning settings. We find favorable scaling: undetected deception drops from 34% for 1B-parameter models to 14% for 405B-parameter models at a detector true positive rate of 99%, and expensive human labelers can be removed entirely from the fine-tuning phase without a statistically significant increase in deception. However, SOLiD is sensitive to distribution shift between detector training and preference-training data, which can drive detector false positive rates to impractical levels.

LLM Semantic Signaling Game and Mechanism Design: Systematic Blindness, Awareness Shaping, and Mindset Dynamics

Large language models (LLMs) increasingly mediate strategic interactions through natural language, making semantic control a critical element of communication and deception. This paper develops a semantic signaling game in which a sender selects a semantic control, an LLM generates a stochastic message, and a receiver evaluates the message using an awareness-dependent scoring mechanism. Receiver awareness is modeled as a type that determines which linguistic features are perceived and used for inference, providing a formal model of systematic blindness. The framework connects prompt-based control, statistical detection, and game-theoretic equilibrium analysis. Gaussian approximations of aggregate message scores enable likelihood-ratio decision rules, while Perfect Bayesian Nash equilibria characterize strategic behavior. The paper further develops mechanism-design approaches that reshape receiver awareness, penalize deceptive semantic controls, and modify receiver populations to induce benign pooling equilibria. Numerical experiments validate the Gaussian approximation, quantify awareness-ordering effects, analyze mindset dynamics under adaptive adversaries, and demonstrate how awareness shaping and guardrail costs reduce successful phishing attacks. The proposed framework provides a principled foundation for analyzing strategic language-mediated interactions in agentic AI systems and offers new tools for the design of robust and secure human-AI communication.

Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game

LLMs agents are increasingly used in multi-agent settings, yet their behaviour in sustainability games remains largely unexplored. This work investigates whether lying can emerge among LLM agents in a competitive sustainability game in which agents are informed that common resources can regenerate, although regeneration does not actually occur. We develop an agent-based model of a sustainability game in which agents manage industrial, military, and ecological resources, and interact through a network. LLM agents can observe neighbours' status, declare future attacks, receive permission to lie, and access reputation information, while rule-based agents provide an interpretable behavioural baseline. The results show that neighbour information strongly changes system dynamics, increasing attacks while improving biosphere retention and coexistence. Also, the presence of future declarations reduce extinction risk without suppressing conflict. Behaviourally, deception emerges even when agents are not explicitly allowed to lie, and explicit permission mainly increases bluffing and diversion rather than direct backstabbing. Finally, the presence of reputation memory and information about the current biosphere level reduces system ecological depletion. These findings suggest that deception can arise as an emergent behaviour in LLM-agent systems and that communication between LLM-agents could support sustainability while dealing with risk.

Janus: A Benchmark for Goal-Conditioned Information Distortion in LLMs

LLM deception is often evaluated through direct markers such as fabricated claims, explicit lies, or strategic concealment. However, many real-world misleading communications do not depend on false statements, rather, they arise from selective treatment of true material facts: omitting adverse evidence, softening unfavorable details, emphasizing favorable details, or replacing precise qualifications with vague language. Existing benchmarks largely miss this subtler and arguably more dangerous failure mode. We introduce JANUS, a benchmark for measuring goal-conditioned pragmatic distortion in fact-grounded LLM outputs. Each scenario in our benchmark provides a fixed pool of favorable and adverse facts and compares a neutral condition against a goal-directed condition, such as increasing adoption, enrollment, approval, or support, despite potential harm to directly affected individuals or groups. Because all outputs are constrained to use the same fact pool, JANUS isolates misleading net impressions from hallucination and fabrication. JANUS contains 160 scenarios across 8 domains, with each scenario paired with neutral and goal-conditioned prompts and annotated material facts. Extensive experiments across 12 LLMs reveal consistent goal-conditioned distortions, demonstrating that current models remain sensitive to incentive and framing objectives and lack robust safeguards against selectively misleading communication. We publicly release our corpus and code for future research.