Before Agent Tells The Lie: Has Deception Already Been Represented?
cs.CL
Submitted: 2026-10-05
Updated: 2026-10-05
Code: https://github.com/Sarah-lii/Deception-Prediction
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents
- AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
- Are Your Agents Upward Deceivers?
- DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios
- Mitigating Deceptive Alignment via Self-Monitoring
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
- GSPR: Aligning LLM Safeguards as Generalizable Safety Policy Reasoners
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems
- Stress Testing Deliberative Alignment for Anti-Scheming Training
- Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents
- Constitutional Black-Box Monitoring for Scheming in LLM Agents
- AI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agents
- The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes
- Qwen3 Technical Report
- BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
- PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say
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