Related papers: Throttling Web Agents Using Reasoning Gates

Web browsers are a portal to the internet, where much of human activity is undertaken. Thus, there has been significant research work in AI agents that interact with the internet through web browsing. However, there is also another…

Agentic AI has significantly extended the capabilities of large language models (LLMs) by enabling complex reasoning and tool use. However, most existing frameworks are tailored to domains such as mathematics, coding, or web automation, and…

AI models have become active decision makers, often acting without human supervision. The rapid advancement of AI technology has already caused harmful incidents that have hurt individuals and societies and AI unfairness in heavily…

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse NLP tasks. Extensive research has explored how to enhance the logical reasoning abilities such as Chain-of-Thought, Chain-of-Thought with…

Language agents increasingly act as web-enabled systems that search, browse, and synthesize information from diverse sources. However, these sources can include unreliable or adversarial content, and the robustness of agents to adversarial…

I explain the shutdown problem: the problem of designing artificial agents that (1) shut down when a shutdown button is pressed, (2) don't try to prevent or cause the pressing of the shutdown button, and (3) otherwise pursue goals…

This position paper proposes a fundamental shift in designing code generation models: treating reasoning depth as a controllable resource. Rather than being an incidental byproduct of prompting, we argue that the trade-off between rapid,…

Agents in the real world must make not only logical but also timely judgments. This requires continuous awareness of the dynamic environment: hazards emerge, opportunities arise, and other agents act, while the agent's reasoning is still…

Cybersecurity demands rigorous and scalable techniques to ensure system correctness, robustness, and resilience against evolving threats. Automated reasoning, encompassing formal logic, theorem proving, model checking, and symbolic…

AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their potentially consequential risks. Prior proposals for governing AI agents primarily target…

Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to…

This paper presents the Artificial Agency Program (AAP), a position and research agenda for building AI systems as reality embedded, resource-bounded agents whose development is driven by curiosity-as-learning-progress under physical and…

This article surveys Cognitive Edge Computing as a practical and methodical pathway for deploying reasoning-capable Large Language Models (LLMs) and autonomous AI agents on resource-constrained devices at the network edge. We present a…

The aim of my Ph.D. thesis concerns Reasoning in Highly Reactive Environments. As reasoning in highly reactive environments, we identify the setting in which a knowledge-based agent, with given goals, is deployed in an environment subject…

Traditional AI reasoning techniques have been used successfully in many domains, including logistics, scheduling and game playing. This paper is part of a project aimed at investigating how such techniques can be extended to coordinate…

When robots share the same workspace with other intelligent agents (e.g., other robots or humans), they must be able to reason about the behaviors of their neighboring agents while accomplishing the designated tasks. In practice,…

The rapid evolution of GUI-enabled agents has rendered traditional CAPTCHAs obsolete. While previous benchmarks like OpenCaptchaWorld established a baseline for evaluating multimodal agents, recent advancements in reasoning-heavy models,…

Recent advancements in Large Language Model (LLM) agents have enabled complex multi-turn agentic tasks requiring extensive tool calling, where conversations can span dozens of API calls with increasingly large context windows. However,…

Retrieval-augmented generation (RAG) agents are increasingly deployed to answer questions over local knowledge bases that cannot be centralized due to knowledge-sovereignty constraints. This results in two recurring failures in production:…

AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, these agents come with inherent risks, including the potential…