Related papers: Plausible but Wrong: A case study on Agentic Failu…
Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a difficult challenge.…
Can quantum mechanics help us in building intelligent robots and agents? One of the defining characteristics of intelligent behavior is the capacity to learn from experience. However, a major bottleneck for agents to learn in any real-life…
The inherent non-deterministic nature of autonomous agents, particularly within low-code/no-code (LCNC) environments, presents significant reliability challenges. Agents can become trapped in unforeseen loops, generate inaccurate outputs,…
Getting a real cybersecurity risk assessment for a small organization is expensive -- a NIST CSF-aligned engagement runs $15,000 on the low end, takes weeks, and depends on practitioners who are genuinely scarce. Most small companies skip…
Frontier AI agents show increasing promise as scientific research assistants, and may eventually be useful for extended, open-ended research workflows. However, in order to use agents for novel research, we must first assess the underlying…
Large Language Models (LLMs), such as OpenAI-o1 and DeepSeek-R1, have demonstrated strong reasoning capabilities. To further enhance LLM capabilities, recent agentic systems, such as Deep Research, incorporate web interactions into LLM…
Large language models are moving scientific research from text assistance toward agentic workflows, yet biological research requires strong object validation, methodological suitability, reproducibility, and auditability. Prompt…
Generative Artificial Intelligence (GenAI) has rapidly transformed various fields including code generation, text summarization, image generation and so on. Agentic AI is a recent evolution that further advances this by coupling the…
The human-agent team, which is a problem in which humans and autonomous agents collaborate to achieve one task, is typical in human-AI collaboration. For effective collaboration, humans want to have an effective plan, but in realistic…
Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck. Current solutions are impractical: fine-tuning requires large annotated datasets scientists often lack, while manual code…
We report a case study of four end-to-end attempts to autonomously generate ML research papers using a pipeline of six LLM agents mapped to stages of the scientific workflow. Of these four, three attempts failed during implementation or…
Over-reliance on AI systems can undermine users' critical thinking and promote complacency, a risk intensified by the emergence of agentic AI systems that operate with minimal human involvement. In software engineering, agentic coding…
Failure attribution in LLM multi-agent systems-identifying the agent and step responsible for task failures-provides crucial clues for systems debugging but remains underexplored and labor-intensive. In this paper, we propose and formulate…
The rise of Agentic applications and automation in the Voice AI industry has led to an increased reliance on Large Language Models (LLMs) to navigate graph-based logic workflows composed of nodes and edges. However, existing methods face…
We examine the problem of adversarial reinforcement learning for multi-agent domains including a rule-based agent. Rule-based algorithms are required in safety-critical applications for them to work properly in a wide range of situations.…
Agentic AI systems, which leverage multiple autonomous agents and large language models (LLMs), are increasingly used to address complex, multi-step tasks. The safety, security, and functionality of these systems are critical, especially in…
Artificial Intelligence is moving from models that only generate text to Agentic AI, where systems behave as autonomous entities that can perceive, reason, plan, and act. Large Language Models (LLMs) are no longer used only as passive…
While Vision-Language-Action (VLA) models have demonstrated impressive capabilities in robotic manipulation, their performance in complex reasoning and long-horizon task planning is limited by data scarcity and model capacity. To address…
Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address. Although recent work by Unit 42 at Palo Alto Networks demonstrated that ChatGPT-4o successfully executes attacks as an agent that it refuses in…
How objective and unbiased are we while making decisions? This work investigates cognitive bias identification in high-stake decision making process by human experts, questioning its effectiveness in real-world settings, such as candidates…