{"total":53,"rows":[{"id":"2502.20073","title":"Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents","created":"2025-02-27","cited_by_count":41,"area":"agents"},{"id":"2407.07087","title":"CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation","created":"2024-07-09","cited_by_count":35,"area":null},{"id":"2502.12197","title":"A Closer Look at System Prompt Robustness","created":"2025-02-15","cited_by_count":32,"area":"safety"},{"id":"2505.20322","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","created":"2025-05-23","cited_by_count":24,"area":null},{"id":"2504.03111","title":"Les Dissonances: Cross-Tool Harvesting and Polluting in Pool-of-Tools Empowered LLM Agents","created":"2025-04-04","cited_by_count":22,"area":"agents"},{"id":"2510.07777","title":"Drift No More? Context Equilibria in Multi-Turn LLM Interactions","created":"2025-10-09","cited_by_count":22,"area":null},{"id":"2505.12025","title":"Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering","created":"2025-05-17","cited_by_count":21,"area":null},{"id":"2507.20152","title":"Goal Alignment in LLM-Based User Simulators for Conversational AI","created":"2025-07-27","cited_by_count":21,"area":null},{"id":"2505.21091","title":"Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)","created":"2025-05-27","cited_by_count":19,"area":null},{"id":"2502.15538","title":"SOTOPIA-$\\Omega$: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents","created":"2025-02-21","cited_by_count":16,"area":"agents"},{"id":"2508.03550","title":"Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations","created":"2025-08-05","cited_by_count":15,"area":"alignment"},{"id":"2512.12775","title":"Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions","created":"2025-12-14","cited_by_count":12,"area":null},{"id":"2604.09212","title":"SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation","created":"2026-04-10","cited_by_count":11,"area":"agents"},{"id":"2410.19406","title":"An Auditing Test To Detect Behavioral Shift in Language Models","created":"2024-10-25","cited_by_count":9,"area":null},{"id":"2503.23306","title":"Focus Directions Make Your Language Models Pay More Attention to Relevant Contexts","created":"2025-03-30","cited_by_count":9,"area":null},{"id":"2605.23932","title":"When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure","created":"2026-04-23","cited_by_count":6,"area":null},{"id":"2606.30571","title":"Attractor States Emerge in Multi-Turn LLM Conversations","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2509.21051","title":"When Instructions Multiply: Measuring and Estimating LLM Capabilities of Multiple Instructions Following","created":"2025-09-25","cited_by_count":5,"area":null},{"id":"2511.04694","title":"Reasoning Up the Instruction Ladder for Controllable Language Models","created":"2025-10-30","cited_by_count":5,"area":"lr"},{"id":"2601.05201","title":"Mechanisms of Prompt-Induced Hallucination in Vision-Language Models","created":"2026-01-08","cited_by_count":5,"area":"mllm"},{"id":"2603.00024","title":"Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2605.24279","title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2505.24613","title":"When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue Generation","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2509.03736","title":"Are LLM Agents Behaviorally Coherent? Latent Profiles for Social Simulation","created":"2025-09-03","cited_by_count":4,"area":"agents"},{"id":"2509.16332","title":"Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2507.21117","title":"A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2603.16152","title":"HIPO: Instruction Hierarchy via Constrained Reinforcement Learning","created":"2026-03-17","cited_by_count":3,"area":"alignment"},{"id":"2609.20822","title":"Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation","created":"2026-09-17","cited_by_count":3,"area":"agents"},{"id":"2510.03223","title":"Attention-Aligned Reasoning for Large Language Models","created":"2025-10-03","cited_by_count":2,"area":"lr"},{"id":"2508.08719","title":"IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2603.18893","title":"Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation","created":"2026-03-19","cited_by_count":1,"area":"mechinterp"},{"id":"2605.02751","title":"Mitigating Misalignment Contagion by Steering with Implicit Traits","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2606.07571","title":"Enabling KV Caching of Shared Prefix for Diffusion Language Models","created":"2026-05-26","cited_by_count":1,"area":"diffusion"},{"id":"2607.01802","title":"On the Limits of Steering Vectors for Preference-Aligned Generation","created":"2026-07-02","cited_by_count":1,"area":"alignment"},{"id":"2608.00023","title":"Role Steering of Language Models for Social Simulations","created":"2026-07-09","cited_by_count":1,"area":"agents"},{"id":"2609.19044","title":"Entropy in Conversational AI: Structured Unpredictability as Inferrable Interiority","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2601.11526","title":"Chatsparent: An Interactive System for Detecting and Mitigating Cognitive Fatigue in LLMs","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2603.01243","title":"Suffix-Constrained Greedy Search Algorithms for Causal Language Models","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2605.06196","title":"The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.18226","title":"Context Memorization for Efficient Long Context Generation","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.21843","title":"Measuring What Persists: Conditioning Mechanisms and a Geometric Framework for AI Agent Identity","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2607.10202","title":"When Counterbalancing Hides the Bias: Access-Conditioned Position Lock in Forced-Choice LLM Evaluation","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.10539","title":"AI YOU Town: Make Friends and Money with Your Digital Twin","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.23545","title":"Language Shapes Instruction Hierarchy Compliance in Multilingual LLMs","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.12599","title":"Dead text or binding clause? Measuring and restoring constraint influence in black-box LLM dialogues","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.19207","title":"Compliance, Capability, and Conflict: Benchmarking Multimodal LLMs under System Messages","created":"2026-06-12","cited_by_count":0,"area":"mllm"},{"id":"2609.08016","title":"What Does Multi-Agent LLM Debate Actually Change? A Layered Analysis of Disagreement and Answer Quality","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.16667","title":"ANIMASK: What the Model Contributes to Role Play in Simulated Story Worlds","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.22607","title":"Pretrained Persona Mixture Models and Tandem Models for Human Simulation","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.36657","title":"Constitutional adapters: Inference-time interventions for misalignment and misuse","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2609.38753","title":"Where the Evidence Lives: Auditing AI Companions' Self-Descriptions","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02664","title":"A GHOST in Long-Horizon Agents: Governance Hazard from Overlooked Safety Constraints across Turns","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.04379","title":"AgentPersonaBench: Benchmarking Persona-Driven User Simulation","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}