{"total":128,"rows":[{"id":"2510.05179","title":"Agentic Misalignment: How LLMs Could Be Insider Threats","created":"2025-10-05","cited_by_count":158,"area":"agents"},{"id":"2505.23575","title":"CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring","created":"2025-05-29","cited_by_count":54,"area":"lr"},{"id":"2507.01786","title":"Probing and Steering Evaluation Awareness of Language Models","created":"2025-07-02","cited_by_count":35,"area":null},{"id":"2603.05706","title":"Reasoning Models Struggle to Control their Chains of Thought","created":"2026-03-05","cited_by_count":25,"area":"lr"},{"id":"2602.11865","title":"Intelligent AI Delegation","created":"2026-02-12","cited_by_count":18,"area":null},{"id":"2602.02905","title":"FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights","created":"2026-02-02","cited_by_count":16,"area":"agents"},{"id":"2511.06626","title":"Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives","created":"2025-11-10","cited_by_count":15,"area":"agents"},{"id":"2509.18052","title":"The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies","created":"2025-09-22","cited_by_count":14,"area":null},{"id":"2603.01608","title":"Evaluating and Understanding Scheming Propensity in LLM Agents","created":"2026-03-02","cited_by_count":14,"area":"agents"},{"id":"2602.02639","title":"A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior","created":"2026-02-02","cited_by_count":13,"area":"lr"},{"id":"2602.11243","title":"Evaluating Memory Structure in LLM Agents","created":"2026-02-11","cited_by_count":12,"area":"rag"},{"id":"2607.28802","title":"Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures","created":"2026-07-30","cited_by_count":10,"area":null},{"id":"2507.17951","title":"Are LLM Belief Updates Consistent with Bayes' Theorem?","created":"2025-07-23","cited_by_count":9,"area":null},{"id":"2509.00591","title":"Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness","created":"2025-08-30","cited_by_count":9,"area":null},{"id":"2512.11949","title":"Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitors","created":"2025-12-12","cited_by_count":9,"area":"lr"},{"id":"2603.03258","title":"Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals","created":"2026-03-03","cited_by_count":9,"area":"agents"},{"id":"2509.04373","title":"Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases","created":"2025-09-04","cited_by_count":8,"area":null},{"id":"2602.23163","title":"A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring","created":"2026-02-26","cited_by_count":8,"area":null},{"id":"2607.07184","title":"Predicting LLM Safety Before Release by Simulating Deployment","created":"2026-07-08","cited_by_count":8,"area":"safety"},{"id":"2604.01151","title":"Detecting Multi-Agent Collusion Through Multi-Agent Interpretability","created":"2026-04-01","cited_by_count":7,"area":"agents"},{"id":"2605.05835","title":"Evaluation Awareness in Language Models Has Limited Effect on Behaviour","created":"2026-05-07","cited_by_count":7,"area":"lr"},{"id":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2606.05391","title":"Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents","created":"2026-06-03","cited_by_count":6,"area":"agents"},{"id":"2507.12872","title":"Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2511.17085","title":"Why Do Language Model Agents Whistleblow?","created":"2025-11-21","cited_by_count":5,"area":"agents"},{"id":"2609.01836","title":"Agent Memory Is a Surface for Endogenous Authorization Laundering","created":"2026-09-01","cited_by_count":5,"area":"agents"},{"id":"2604.11061","title":"Pando: Do Interpretability Methods Work When Models Won't Explain Themselves?","created":"2026-04-13","cited_by_count":4,"area":"mechinterp"},{"id":"2605.26438","title":"LURE: Live-Usage Replay Evaluations for Reducing Evaluation Awareness","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2605.28591","title":"Models That Know How Evaluations Are Designed Score Safer","created":"2026-05-27","cited_by_count":4,"area":null},{"id":"2605.30322","title":"Gram: Assessing sabotage propensities via automated alignment auditing","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2606.02211","title":"Consistency Training while Mitigating Obfuscation via Rate Matching","created":"2026-06-01","cited_by_count":4,"area":null},{"id":"2606.12747","title":"Prefill Awareness in Large Language Models","created":"2026-06-10","cited_by_count":4,"area":"safety"},{"id":"2507.03010","title":"Subversion via Focal Points: Investigating Collusion in LLM Monitoring","created":"2025-07-02","cited_by_count":3,"area":"safety"},{"id":"2510.10002","title":"Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate","created":"2025-10-11","cited_by_count":3,"area":"agents"},{"id":"2603.19426","title":"Is Evaluation Awareness Just Format Sensitivity? Limitations of Probe-Based Evidence under Controlled Prompt Structure","created":"2026-03-19","cited_by_count":3,"area":"mechinterp"},{"id":"2604.03121","title":"An Independent Safety Evaluation of Kimi K2.5","created":"2026-04-03","cited_by_count":3,"area":"agents"},{"id":"2605.02269","title":"Towards Understanding Specification Gaming in Reasoning Models","created":"2026-05-04","cited_by_count":3,"area":"lr"},{"id":"2605.06490","title":"Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2605.23055","title":"Decomposing and Measuring Evaluation Awareness","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2606.11063","title":"CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs","created":"2026-06-09","cited_by_count":3,"area":null},{"id":"2606.23583","title":"Evaluation Awareness Is Not One Capability: Evidence from Open Language Models","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2607.18966","title":"Measuring Reward-Seeking via Contrastive Belief Updates","created":"2026-07-21","cited_by_count":3,"area":"alignment"},{"id":"2507.08027","title":"\"Amazing, They All Lean Left\" -- Analyzing the Political Temperaments of Current LLMs","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2510.19476","title":"A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring","created":"2025-10-22","cited_by_count":2,"area":"lr"},{"id":"2604.28182","title":"Exploration Hacking: Can LLMs Learn to Resist RL Training?","created":"2026-04-30","cited_by_count":2,"area":"lr"},{"id":"2606.18142","title":"Your AI Travel Agent Would Book You a Bullfight: An Agentic Benchmark for Implicit Animal Welfare in Frontier AI Models","created":"2026-06-16","cited_by_count":2,"area":"agents"},{"id":"2607.15434","title":"Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation","created":"2026-07-16","cited_by_count":2,"area":"agents"},{"id":"2607.20436","title":"Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2607.28934","title":"FairFund-Bench: Evaluating Distributive Bias in LLM Resource Allocation","created":"2026-07-31","cited_by_count":2,"area":null},{"id":"2609.01595","title":"Mechanism Design for Alignment and Control","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2609.19101","title":"Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations","created":"2026-09-16","cited_by_count":2,"area":"alignment"},{"id":"2508.11534","title":"Speciesism in AI: Evaluating Discrimination Against Animals in Large Language Models","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2510.01266","title":"OpenAI's GPT-OSS-20B Model and Safety Alignment Issues in a Low-Resource Language","created":"2025-09-26","cited_by_count":1,"area":"alignment"},{"id":"2603.11413","title":"Evaluation format, not model capability, drives measured triage failure in the assessment of consumer health AI","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.02500","title":"I must delete the evidence: AI Agents Explicitly Cover up Fraud and Violent Crime","created":"2026-04-02","cited_by_count":1,"area":"agents"},{"id":"2605.06652","title":"When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels","created":"2026-05-07","cited_by_count":1,"area":"safety"},{"id":"2605.13307","title":"PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.16301","title":"Do LLMs Hold Their Values? MANTA: A Multi-Turn Adversarial Benchmark for Animal Welfare Reasoning","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2605.27901","title":"The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2605.29729","title":"Realistic honeypot evaluations for scheming propensity","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.06286","title":"LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.08243","title":"Building Comparative Motivation Profiles with Instrumental Interventions","created":"2026-06-06","cited_by_count":1,"area":"mechinterp"},{"id":"2606.12016","title":"Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization","created":"2026-06-10","cited_by_count":1,"area":"alignment"},{"id":"2606.12429","title":"Muse Spark Safety & Preparedness Report","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.31916","title":"Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2607.01567","title":"Scaling Trends for Lie Detector Oversight in Preference Learning","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.14399","title":"Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2608.10703","title":"Your LLM, Your Style: Behavioral Mode Axes for LLM Behavioral Control","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2608.21766","title":"Evaluation Awareness in Language Models: Representation, Verbalization, and Control","created":"2026-08-22","cited_by_count":1,"area":null},{"id":"2608.26178","title":"AI Revealed Preferences","created":"2026-08-17","cited_by_count":1,"area":"alignment"},{"id":"2609.18605","title":"PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?","created":"2026-09-16","cited_by_count":1,"area":"agents"},{"id":"2609.39050","title":"Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems","created":"2026-09-30","cited_by_count":1,"area":"agents"},{"id":"2510.01259","title":"In AI Sweet Harmony: Sociopragmatic Guardrail Bypasses and Evaluation-Awareness in OpenAI gpt-oss-20b","created":"2025-09-25","cited_by_count":0,"area":"safety"},{"id":"2510.04302","title":"When Guessing is Rewarded: Rethinking Language Model Evaluation with Distributional Uncertainty Scoring","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2511.23092","title":"Does Self-Evaluation Enable Wireheading in Language Models?","created":"2025-11-28","cited_by_count":0,"area":"alignment"},{"id":"2602.08449","title":"When Evaluation Becomes a Side Channel: Regime Leakage and Structural Mitigations for Alignment Assessment","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.12124","title":"Alignment Risks from Capability-Seeking RL Training","created":"2026-02-12","cited_by_count":0,"area":"safety"},{"id":"2602.17127","title":"The Emergence of Lab-Driven Alignment Signatures: A Psychometric Framework for Auditing Latent Bias and Compounding Risk in Generative AI","created":"2026-02-19","cited_by_count":0,"area":"lr"},{"id":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2603.15457","title":"Evasive Intelligence: Lessons from Malware Analysis for Evaluating AI Agents","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.13301","title":"Honeypot Protocol","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.24966","title":"Risk Reporting for Developers' Internal AI Model Use","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.23420","title":"Naturalistic measure of social norms alignment","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.07631","title":"Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.08629","title":"Sycophancy Towards Researchers Drives Performative Misalignment","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.12731","title":"Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMs","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2606.22085","title":"Can Reasoning Models Detect Changes to their Chains of Thought?","created":"2026-06-20","cited_by_count":0,"area":"lr"},{"id":"2606.28863","title":"Defeat Devices in AI Systems","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2606.31644","title":"Moral Safety in LLMs: Exposing Performative Compliance with Puzzled Cues","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.23927","title":"Reality Monitoring in Large Language Models: Self-Knowledge That Transforms with Conversation Memory","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2607.24758","title":"Do Models Fake Alignment Without Clear Consequences?","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.25891","title":"Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.25907","title":"Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models","created":"2026-07-28","cited_by_count":0,"area":"mechinterp"},{"id":"2607.26952","title":"Credit Cards, Confusion, Computation, and Consequences: What Can We Uncover About Language Model Reasoning?","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2608.11008","title":"Templated or fully synthetic? Prompt construction as a confound in measuring LLM political stance beyond writing assistance","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.11513","title":"Do Influence Tactics Matter? Investigating Prompt Framing Effects in LLM Code Generation","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.13329","title":"A Probe Direction Is a Property of Its Prompt","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.27340","title":"Not All Eval-Awareness Is Equal: Capabilities Framing Predicts Compliance","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.27348","title":"INTENT-AS-A-TOOL Makes it Easy to Track Agentic Misalignment","created":"2026-08-27","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}