{"total":39,"rows":[{"id":"2502.02542","title":"OverThink: Slowdown Attacks on Reasoning LLMs","created":"2025-02-04","cited_by_count":96,"area":"lr"},{"id":"2503.24370","title":"Effectively Controlling Reasoning Models through Thinking Intervention","created":"2025-03-31","cited_by_count":65,"area":"lr"},{"id":"2501.18841","title":"Trading Inference-Time Compute for Adversarial Robustness","created":"2025-01-31","cited_by_count":61,"area":"lr"},{"id":"2509.11035","title":"Free-MAD: Consensus-Free Multi-Agent Debate","created":"2025-09-14","cited_by_count":29,"area":"lr"},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"area":"lr"},{"id":"2507.20526","title":"Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition","created":"2025-07-28","cited_by_count":24,"area":"lr"},{"id":"2503.01781","title":"Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Models","created":"2025-03-03","cited_by_count":23,"area":"lr"},{"id":"2402.01108","title":"Reasoning Capacity in Multi-Agent Systems: Limitations, Challenges and Human-Centered Solutions","created":"2024-02-02","cited_by_count":17,"area":"lr"},{"id":"2509.24967","title":"SecInfer: Preventing Prompt Injection via Inference-time Scaling","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2609.31142","title":"JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models","created":"2026-09-25","cited_by_count":10,"area":"lr"},{"id":"2603.03205","title":"Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use","created":"2026-03-03","cited_by_count":8,"area":"lr"},{"id":"2603.07379","title":"SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions","created":"2026-03-07","cited_by_count":8,"area":"lr"},{"id":"2508.20737","title":"Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol","created":"2025-08-28","cited_by_count":6,"area":"lr"},{"id":"2603.27517","title":"A Security Analysis of the OpenClaw AI Agent Framework","created":"2026-03-29","cited_by_count":5,"area":"lr"},{"id":"2506.21967","title":"More Vulnerable than You Think: On the Stability of Tool-Integrated LLM Agents","created":"2025-06-27","cited_by_count":3,"area":"lr"},{"id":"2603.15661","title":"DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs","created":"2026-03-09","cited_by_count":3,"area":"lr"},{"id":"2605.12460","title":"Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2510.06002","title":"Deterministic Legal Agents: A Canonical Primitive API for Auditable Reasoning over Temporal Knowledge Graphs","created":"2025-10-07","cited_by_count":2,"area":"lr"},{"id":"2602.01795","title":"RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache Reuse","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2604.25684","title":"Think Before You Act -- A Neurocognitive Governance Model for Autonomous AI Agents","created":"2026-04-28","cited_by_count":2,"area":"lr"},{"id":"2606.05976","title":"The Self-Correction Illusion: Role Relabeling Gates Explicit Error Flagging in Large Language Models","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2607.08066","title":"Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2602.17022","title":"ReIn: Conversational Error Recovery with Reasoning Inception","created":"2026-02-19","cited_by_count":1,"area":"lr"},{"id":"2605.27932","title":"When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.08234","title":"SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents","created":"2026-06-06","cited_by_count":1,"area":"lr"},{"id":"2508.15839","title":"CIA+TA Risk Assessment for AI Reasoning Vulnerabilities","created":"2025-08-19","cited_by_count":0,"area":"lr"},{"id":"2602.04856","title":"CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation","created":"2026-02-04","cited_by_count":0,"area":"lr"},{"id":"2605.07138","title":"Can You Break RLVER? Probing Adversarial Robustness of RL-Trained Empathetic Agents","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.12746","title":"CoT-Guard: Small Models for Strong Monitoring","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.30686","title":"Depth-Dependent Indirect Prompt Injection in Tool-Calling ReAct Agents: Injection Depth, Payload Framing, and Turn-Budget Sensitivity","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"id":"2606.07808","title":"Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2606.19588","title":"Analyzing the Narration Gap in LLM-Solver Loops","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"id":"2607.08180","title":"Out of Sight: Compression-Aware Content Protection against Agentic Crawlers","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2608.15392","title":"Visible Reasoning and Indirect Prompt-Injection Monitorability Across English, Tamil, and Tanglish","created":"2026-08-15","cited_by_count":0,"area":"lr"},{"id":"2609.02754","title":"Untangling the Mechanisms of Misleading Context in Medical Question Answering","created":"2026-09-02","cited_by_count":0,"area":"lr"},{"id":"2609.39146","title":"MADBench: Benchmarking the Security of Multi-Agent Debate","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.05241","title":"StateWise: Diagnosing and Repairing Persistent Operational State Before Agent Actions","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.08923","title":"AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.18566","title":"Rethinking Quality in Large Language Model Routing: Security-Conditioned Model-and-Budget Selection","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}