arXiv AI
Jun 6
Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
arXiv:2503. 01734v3 Announce Type: replace-cross Abstract: Attacks on machine learning models have been extensively studied through stateless optimization.
AI agents
Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv AI
Jun 6
DPBench: Structural Determinants of Multi-Agent LLM Coordination Under Simultaneous Resource Contention
arXiv:2602. 13255v2 Announce Type: replace Abstract: We present DPBench, a benchmark for evaluating coordination in multi-agent systems built from large language models.
arXiv AI
Jun 6
Data Flow Control: Data Safety Policies for AI Agents
arXiv:2606. 05679v1 Announce Type: cross Abstract: Agents increasingly generate SQL, orchestrate pipelines, and automate data analysis on behalf of users.
arXiv AI
Jun 6
AutoDFT: A Closed-Loop Multi-Agent Framework for Autonomous DFT Calculations
arXiv:2605. 26179v2 Announce Type: replace-cross Abstract: Density functional theory (DFT) serves as the basis for computational discovery in materials science and chemistry, yet each calculation demands extensive human effort: adjusting algorithms when convergence stalls, revising plans when unexpected physics emerges, and inserting steps as intermediate results reshape the problem.
arXiv AI
Jun 6
TensorBench: Benchmarking Coding Agents on a Compiler-Based Tensor Framework
arXiv:2606. 05570v1 Announce Type: cross Abstract: Repository-level coding benchmarks face a trade-off between task difficulty and evaluation reliability: tasks that challenge frontier models often involve large codebases with incomplete test coverage, while human review does not scale.
arXiv AI
Jun 6
Evaluating Agentic Configuration Repair for Computer Networks
arXiv:2606. 06212v1 Announce Type: new Abstract: Misconfigurations in computer networks remain a major source of critical Internet outages.
arXiv AI
Jun 6
RiskFlow: Fast and Faithful Safety-Critical Traffic Scenario Generation
arXiv:2606. 06423v1 Announce Type: cross Abstract: Safety-critical traffic scenario generation is essential for evaluating autonomous driving systems under rare but high-risk interactions.
arXiv AI
Jun 6
Evidence Over Plans: Online Trajectory Verification for Skill Distillation
arXiv:2605. 09192v2 Announce Type: replace Abstract: Agent skills can remarkably improve task success rates by using human-written procedural documents, but their quality is difficult to assess without environment-grounded verification.
arXiv AI
Jun 6
Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming
arXiv:2606. 05233v1 Announce Type: cross Abstract: Recent computer-using-agent (CUA) red-teaming papers report prompt-injection attack success rates (ASR) of 42-98%, but these headline numbers cluster on retired models and on the most-vulnerable model in each paper's panel.
arXiv AI
Jun 6
Output Type Before Quality: A Standards-Derived XAI Admissibility Rubric for Autonomous-Driving Safety
arXiv:2606. 05461v1 Announce Type: new Abstract: Safety standards for ML-based autonomous driving specify the kind of evidence an assurance case must contain (directed cause-and-effect chains, quantified interventional effects, named root-cause variables), yet the XAI literature is organised by output type and technique family (saliency maps, feature attribution, counterfactuals, causal graphs, language traces).
arXiv AI
Jun 6
PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation
arXiv:2606. 05697v1 Announce Type: new Abstract: User interface (UI) and user experience (UX) evaluation is central to product development, yet reliable feedback still relies on recruiting human participants or running online A/B tests, making early-stage iteration slow and costly.
arXiv AI
Jun 6
VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents
arXiv:2606. 05395v1 Announce Type: cross Abstract: Reusable robot skills are becoming the basic units through which embodied agents turn open-ended instructions into long-horizon physical behavior.
arXiv AI
Jun 6
Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents
arXiv:2606. 06090v1 Announce Type: new Abstract: LLM-based agents increasingly tackle long-horizon tasks with interdependent decisions, where each action reshapes future constraints and intermediate errors can cascade.
arXiv AI
Jun 6
Emergent Language as an Approach to Conscious AI
arXiv:2606. 06380v1 Announce Type: cross Abstract: The question of whether artificial systems can be conscious remains open, in part because existing approaches either evaluate systems against theory-derived checklists (discriminative) or engineer consciousness-inspired modules directly (architectural); both leave open whether observed structures are artifacts of human language priors.
arXiv AI
Jun 6
Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments
arXiv:2606. 05661v1 Announce Type: new Abstract: Continual learning, the ability of AI systems to improve through sequential experience, has attracted substantial interest, but no high-quality benchmark exists to evaluate it.
arXiv AI
Jun 6
Statistical Priors for Implicit Preferences: Decoupling Skill Selection as a Local Harness in Personal Agents
arXiv:2606. 05828v1 Announce Type: new Abstract: As Large Language Model (LLM) capabilities advance, locally deployed personal agents relying on API-based remote models and external skills have emerged as a novel paradigm.
arXiv AI
Jun 6
Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents
arXiv:2606. 05391v1 Announce Type: cross Abstract: Autonomous software agents hold promise to increase developer productivity but make mistakes and exhibit novel failure modes, making human oversight central to successful human-agent collaboration.
arXiv AI
Jun 6
SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents
arXiv:2606. 05761v1 Announce Type: new Abstract: Persistent AI assistants, such as OpenClaw, accumulate large collections of related memories over long-term interactions.
arXiv AI
Jun 6
CangLing-KnowFlow: A Unified Knowledge-and-Flow-fused Agent for Comprehensive Remote Sensing Applications
arXiv:2512. 15231v3 Announce Type: replace Abstract: The automated and intelligent processing of massive remote sensing (RS) datasets is critical in Earth observation (EO).
arXiv AI
Jun 6
Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation
arXiv:2606. 05660v1 Announce Type: cross Abstract: Embodied AI systems are increasingly expected to reason and act over extended horizons in physical environments.