{"total":26,"rows":[{"id":"2606.22936","title":"When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents","created":"2026-06-22","cited_by_count":10,"area":"agents"},{"id":"2606.22864","title":"When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents","created":"2026-06-22","cited_by_count":7,"area":"agents"},{"id":"2608.02657","title":"Your Agentic LLMs Secretly Encode Indirect Prompt-Injection Exposure in Hidden States","created":"2026-08-01","cited_by_count":7,"area":"agents"},{"id":"2502.14171","title":"Enhancing Conversational Agents with Theory of Mind: Aligning Beliefs, Desires, and Intentions for Human-Like Interaction","created":"2025-02-20","cited_by_count":3,"area":"agents"},{"id":"2606.22673","title":"AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent","created":"2026-06-21","cited_by_count":3,"area":"agents"},{"id":"2603.12564","title":"Sell Me This Stock: Unsafe Recommendation Drift in LLM Agents","created":"2026-03-13","cited_by_count":2,"area":"agents"},{"id":"2603.16335","title":"Behavioral Steering in a 35B MoE Language Model via SAE-Decoded Probe Vectors: One Agency Axis, Not Five Traits","created":"2026-03-17","cited_by_count":1,"area":"agents"},{"id":"2607.05188","title":"Latent Programming Horizons in Coding Agents","created":"2026-07-06","cited_by_count":1,"area":"agents"},{"id":"2607.16448","title":"Retrieval is Enough: Training-Free Interpretability with a Tool-Using Agent","created":"2026-07-17","cited_by_count":1,"area":"agents"},{"id":"2609.13529","title":"Generative Interpretability via Scalable Neuro-Symbolic Models","created":"2026-09-11","cited_by_count":1,"area":"agents"},{"id":"2609.15982","title":"The Router Within: Eliciting Native Skill Routing from a Frozen LLM","created":"2026-09-14","cited_by_count":1,"area":"agents"},{"id":"2609.27286","title":"Memory Control Signals Emerge Before Action in Long Horizon Agents","created":"2026-09-23","cited_by_count":1,"area":"agents"},{"id":"2609.36642","title":"PR-OPD: Privileged Representation On-policy Self-Distillation for Agentic Reinforcement Learning","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2610.00400","title":"Representation Transitions Reveal Emerging Safety Risks in Multi-Turn LLM Agents","created":"2026-09-30","cited_by_count":1,"area":"agents"},{"id":"2602.00959","title":"Probing the Knowledge Boundary: An Interactive Agentic Framework for Deep Knowledge Extraction","created":"2026-02-01","cited_by_count":0,"area":"agents"},{"id":"2605.12411","title":"Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling","created":"2026-05-12","cited_by_count":0,"area":"agents"},{"id":"2605.18918","title":"ESLD (External Surrogate Latent Defense): A Latent-Space Architecture for Faster, Stronger Prompt-Injection Defense","created":"2026-05-18","cited_by_count":0,"area":"agents"},{"id":"2606.10304","title":"MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents","created":"2026-06-09","cited_by_count":0,"area":"agents"},{"id":"2608.20393","title":"Knowledge-Graph-Gated Defactualization for Style-Controllable and Fact-Preserving Generation in Agentic Conversational AI","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2609.16270","title":"Cheap Talk Stabilizes Strategic Interaction in LLM Agents","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.18357","title":"Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2610.04575","title":"From Probe Scores to Alarm Policies: Operational Validity of Activation Monitors for Language-Model Agents","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.16141","title":"Phantom Merge: When Your Large Language Model Agents Pick One but Tell You About Another","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17365","title":"When Goals Leak Across Relationships: How Cached Goal Representations Shape Cross-Client Decisions","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17444","title":"The belief-action gap in language model agents","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.19679","title":"MCAIR: Monitoring and Correcting Agent Unfaithfulness via Internal Representations","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}