{"total":15,"rows":[{"id":"2605.07990","title":"Tool Calling is Linearly Readable and Steerable in Language Models","created":"2026-05-08","cited_by_count":10,"area":"agents"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"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":"2606.06976","title":"Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning","created":"2026-06-05","cited_by_count":4,"area":"agents"},{"id":"2605.06890","title":"Beyond the Black Box: Interpretability of Agentic AI Tool Use","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2608.00218","title":"A Few Neurons Reveal When LLMs Misuse Tools: Sparse Detection and Selective Steering for Reliable Tool Use","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2608.10430","title":"Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique","created":"2026-08-11","cited_by_count":2,"area":"agents"},{"id":"2605.25310","title":"Tool-Call Dependency Structure is Linearly Decodable in LLM Agent Residual Streams","created":"2026-05-25","cited_by_count":1,"area":"agents"},{"id":"2609.05274","title":"How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate Method","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"id":"2608.03071","title":"Getting the Parameters Right: A Difficulty-Graded Benchmark and Probe-Guided Training for LLM Tool Calls","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2608.07531","title":"Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards","created":"2026-07-24","cited_by_count":0,"area":"agents"},{"id":"2608.27750","title":"The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2609.07395","title":"Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.09448","title":"Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representations","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.36138","title":"When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs","created":"2026-09-28","cited_by_count":0,"area":"agents"}],"next_cursor":null}