{"total":116,"rows":[{"id":"2507.21046","title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","created":"2025-07-28","cited_by_count":170,"area":"agents"},{"id":"2508.14111","title":"From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery","created":"2025-08-18","cited_by_count":77,"area":"agents"},{"id":"2506.04133","title":"TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems","created":"2025-06-04","cited_by_count":59,"area":"agents"},{"id":"2506.23260","title":"From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows","created":"2025-06-29","cited_by_count":58,"area":"agents"},{"id":"2506.19676","title":"A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures","created":"2025-06-24","cited_by_count":57,"area":"agents"},{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2506.07022","title":"AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint","created":"2025-06-08","cited_by_count":49,"area":"safety"},{"id":"2505.19443","title":"Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI","created":"2025-05-26","cited_by_count":42,"area":"agents"},{"id":"2505.22323","title":"Advancing Expert Specialization for Better MoE","created":"2025-05-28","cited_by_count":39,"area":"moe"},{"id":"2506.14697","title":"AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions","created":"2025-06-17","cited_by_count":38,"area":"mllm"},{"id":"2509.23040","title":"Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents","created":"2025-09-27","cited_by_count":38,"area":"lr"},{"id":"2510.09781","title":"Building a Foundational Guardrail for General Agentic Systems via Synthetic Data","created":"2025-10-10","cited_by_count":29,"area":"agents"},{"id":"2506.13666","title":"We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems","created":"2025-06-16","cited_by_count":27,"area":"agents"},{"id":"2507.19227","title":"Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation","created":"2025-07-25","cited_by_count":26,"area":"lr"},{"id":"2508.17692","title":"LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios","created":"2025-08-25","cited_by_count":26,"area":"lr"},{"id":"2510.04040","title":"FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning","created":"2025-10-05","cited_by_count":26,"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":"2505.17716","title":"Get Experience from Practice: LLM Agents with Record & Replay","created":"2025-05-23","cited_by_count":23,"area":"agents"},{"id":"2509.19870","title":"FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models","created":"2025-09-24","cited_by_count":21,"area":"vla"},{"id":"2506.02040","title":"Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem","created":"2025-05-31","cited_by_count":19,"area":"agents"},{"id":"2509.01909","title":"Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models","created":"2025-09-02","cited_by_count":19,"area":"alignment"},{"id":"2509.03888","title":"False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize","created":"2025-09-04","cited_by_count":19,"area":null},{"id":"2607.10487","title":"Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents","created":"2026-07-11","cited_by_count":18,"area":"agents"},{"id":"2505.08807","title":"Security of Internet of Agents: Attacks and Countermeasures","created":"2025-05-12","cited_by_count":17,"area":"agents"},{"id":"2506.20966","title":"Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends","created":"2025-06-26","cited_by_count":17,"area":"mllm"},{"id":"2508.09210","title":"MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models","created":"2025-08-11","cited_by_count":17,"area":"mllm"},{"id":"2507.00841","title":"SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents","created":"2025-07-01","cited_by_count":15,"area":"safety"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2507.21407","title":"Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects","created":"2025-07-29","cited_by_count":14,"area":"agents"},{"id":"2510.11108","title":"A Vision for Access Control in LLM-based Agent Systems","created":"2025-10-13","cited_by_count":14,"area":"agents"},{"id":"2512.01939","title":"An Empirical Study of Agent Developer Practices in AI Agent Frameworks","created":"2025-12-01","cited_by_count":14,"area":"agents"},{"id":"2606.20023","title":"When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents","created":"2026-06-18","cited_by_count":13,"area":"agents"},{"id":"2506.15170","title":"From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem","created":"2025-06-18","cited_by_count":12,"area":"agents"},{"id":"2508.11733","title":"SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication","created":"2025-08-15","cited_by_count":12,"area":"agents"},{"id":"2510.16492","title":"Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety","created":"2025-10-18","cited_by_count":12,"area":"agents"},{"id":"2510.20956","title":"Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training","created":"2025-10-23","cited_by_count":12,"area":"lr"},{"id":"2509.21761","title":"Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models","created":"2025-09-26","cited_by_count":10,"area":"safety"},{"id":"2603.25184","title":"Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model","created":"2026-03-26","cited_by_count":10,"area":"lr"},{"id":"2505.19139","title":"The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework","created":"2025-05-25","cited_by_count":9,"area":null},{"id":"2506.07121","title":"Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models","created":"2025-06-08","cited_by_count":9,"area":"safety"},{"id":"2602.02455","title":"Drift-Bench: Diagnosing Cooperative Breakdowns in LLM Agents under Input Faults via Multi-Turn Interaction","created":"2026-02-02","cited_by_count":9,"area":"agents"},{"id":"2602.12966","title":"ProbeLLM: Automating Principled Diagnosis of LLM Failures","created":"2026-02-13","cited_by_count":9,"area":null},{"id":"2505.16241","title":"Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers","created":"2025-05-22","cited_by_count":8,"area":"lr"},{"id":"2506.00509","title":"Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems","created":"2025-05-31","cited_by_count":8,"area":"agents"},{"id":"2508.02175","title":"Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment through Latent Acoustic Pattern Triggers","created":"2025-08-04","cited_by_count":8,"area":"safety"},{"id":"2511.12710","title":"Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs","created":"2025-11-16","cited_by_count":8,"area":"safety"},{"id":"2602.03100","title":"Risky-Bench: Probing Agentic Safety Risks under Real-World Deployment","created":"2026-02-03","cited_by_count":8,"area":"agents"},{"id":"2605.29801","title":"AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security","created":"2026-05-28","cited_by_count":8,"area":"agents"},{"id":"2505.06643","title":"Practical Reasoning Interruption Attacks on Reasoning Large Language Models","created":"2025-05-10","cited_by_count":7,"area":"lr"},{"id":"2505.19108","title":"CCHall: A Novel Benchmark for Joint Cross-Lingual and Cross-Modal Hallucinations Detection in Large Language Models","created":"2025-05-25","cited_by_count":7,"area":"lr"},{"id":"2509.24610","title":"OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment","created":"2025-09-29","cited_by_count":7,"area":"alignment"},{"id":"2605.02900","title":"Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses","created":"2026-03-28","cited_by_count":7,"area":"safety"},{"id":"2606.10749","title":"Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation","created":"2026-06-09","cited_by_count":7,"area":"agents"},{"id":"2508.17677","title":"TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training","created":"2025-08-25","cited_by_count":6,"area":null},{"id":"2509.06982","title":"CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention","created":"2025-09-01","cited_by_count":6,"area":"alignment"},{"id":"2509.23573","title":"Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2509.24240","title":"Takedown: How It's Done in Modern Coding Agent Exploits","created":"2025-09-29","cited_by_count":6,"area":"agents"},{"id":"2509.24380","title":"Agentic Services Computing","created":"2025-09-29","cited_by_count":6,"area":"agents"},{"id":"2512.00520","title":"Toward a Safe Internet of Agents","created":"2025-11-29","cited_by_count":6,"area":"agents"},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2505.15674","title":"UniErase: Towards Balanced and Precise Unlearning in Language Models","created":"2025-05-21","cited_by_count":5,"area":"safety"},{"id":"2507.04365","title":"Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs","created":"2025-07-06","cited_by_count":5,"area":"safety"},{"id":"2510.19420","title":"Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation","created":"2025-10-22","cited_by_count":4,"area":"agents"},{"id":"2511.14900","title":"Skin-R1: Clinical Knowledge-Guided Dermatological Diagnosis Using Vision-Language Models","created":"2025-11-18","cited_by_count":4,"area":"mllm"},{"id":"2603.23268","title":"SafeSeek: Universal Attribution of Safety Circuits in Language Models","created":"2026-03-24","cited_by_count":4,"area":"safety"},{"id":"2605.16282","title":"Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents","created":"2026-04-11","cited_by_count":4,"area":"agents"},{"id":"2602.14281","title":"MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents","created":"2026-02-15","cited_by_count":3,"area":"agents"},{"id":"2604.16321","title":"LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review","created":"2026-02-25","cited_by_count":3,"area":"agents"},{"id":"2605.25603","title":"Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy","created":"2026-05-25","cited_by_count":3,"area":"lr"},{"id":"2605.28201","title":"Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents","created":"2026-05-27","cited_by_count":3,"area":"agents"},{"id":"2505.22067","title":"From Failures to Fixes: LLM-Driven Scenario Repair for Self-Evolving Autonomous Driving","created":"2025-05-28","cited_by_count":2,"area":"synth"},{"id":"2510.14620","title":"Code-driven Number Sequence Calculation: Enhancing the inductive Reasoning Abilities of Large Language Models","created":"2025-10-16","cited_by_count":2,"area":"lr"},{"id":"2601.19051","title":"Proactive Hardening of LLM Defenses with HASTE","created":"2026-01-27","cited_by_count":2,"area":"safety"},{"id":"2601.22737","title":"Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models","created":"2026-01-30","cited_by_count":2,"area":"mllm"},{"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":"2603.14975","title":"Why Agents Compromise Safety Under Pressure","created":"2026-03-16","cited_by_count":2,"area":"agents"},{"id":"2607.11698","title":"Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming","created":"2026-07-13","cited_by_count":2,"area":"agents"},{"id":"2608.14590","title":"Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement","created":"2026-06-22","cited_by_count":2,"area":"agents"},{"id":"2505.14015","title":"AUTOLAW: Enhancing Legal Compliance in Large Language Models via Case Law Generation and Jury-Inspired Deliberation","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2505.23873","title":"KGMark: A Diffusion Watermark for Knowledge Graphs","created":"2025-05-29","cited_by_count":1,"area":"safety"},{"id":"2511.19569","title":"An Invariant Latent Space Perspective on Language Model Inversion","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2601.10496","title":"Model See, Model Do? Exposure-Aware Evaluation of Bug-vs-Fix Preference in Code LLMs","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2601.19507","title":"Automated Safety Benchmarking: A Multi-agent Pipeline for LVLMs","created":"2026-01-27","cited_by_count":1,"area":"mllm"},{"id":"2602.02557","title":"The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.05401","title":"BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models","created":"2026-02-05","cited_by_count":1,"area":"safety"},{"id":"2602.07259","title":"Incentive-Aware AI Safety via Strategic Resource Allocation: A Stackelberg Security Games Perspective","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2602.14518","title":"Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning","created":"2026-02-16","cited_by_count":1,"area":"lr"},{"id":"2603.05772","title":"Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads","created":"2026-03-06","cited_by_count":1,"area":"safety"},{"id":"2603.07496","title":"From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents","created":"2026-03-08","cited_by_count":1,"area":"agents"},{"id":"2603.08800","title":"Granulon: Awakening Pixel-Level Visual Encoders with Adaptive Multi-Granularity Semantics for MLLM","created":"2026-03-09","cited_by_count":1,"area":"mllm"},{"id":"2603.10194","title":"MCP-in-SoS: Risk assessment framework for open-source MCP servers","created":"2026-03-10","cited_by_count":1,"area":"agents"},{"id":"2604.05540","title":"Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2604.11309","title":"The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems","created":"2026-04-13","cited_by_count":1,"area":"safety"},{"id":"2605.01899","title":"Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment","created":"2026-05-03","cited_by_count":1,"area":"alignment"},{"id":"2605.11679","title":"Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion","created":"2026-05-12","cited_by_count":1,"area":"alignment"},{"id":"2605.12529","title":"BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models","created":"2026-04-15","cited_by_count":1,"area":"safety"},{"id":"2605.20641","title":"Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs","created":"2026-05-20","cited_by_count":1,"area":"safety"},{"id":"2605.29396","title":"Aligned but Fragile: Enhancing LLM Safety Robustness via Zeroth-Order Optimization","created":"2026-05-28","cited_by_count":1,"area":"alignment"},{"id":"2606.25442","title":"PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models","created":"2026-06-24","cited_by_count":1,"area":"alignment"},{"id":"2507.10156","title":"Introducing the Swiss Food Knowledge Graph: AI for Context-Aware Nutrition Recommendation","created":"2025-07-14","cited_by_count":0,"area":null}],"next_cursor":"100"}