Related papers: Throttling Web Agents Using Reasoning Gates
Different types of reasoning impose different structural demands on representational systems, yet no systematic account of these demands exists across psychology, AI, and philosophy of mind. I propose a framework identifying four structural…
We investigate the disruption of discrete-time consensus problems via grounding. Loosely speaking, grounding a network occurs if the state of one agent no longer responds to inputs from other agents and/or changes its dynamics. Then, the…
The wide adoption of AI agents in complex human workflows is driving rapid growth in LLM token consumption. When agents are deployed on tasks that require a significant amount of tokens, three questions naturally arise: (1) Where do AI…
The rise of multi-agent systems powered by large language models (LLMs) and specialized reasoning agents exposes fundamental limitations in today's data management architectures. Traditional databases and data fabrics were designed for…
Language agents powered by large language models (LLMs) have demonstrated remarkable capabilities in understanding, reasoning, and executing complex tasks. However, developing robust agents presents significant challenges: substantial…
The increasing complexity and scale of modern telecommunications networks demand intelligent automation to enhance efficiency, adaptability, and resilience. Agentic AI has emerged as a key paradigm for intelligent communications and…
Computer agents powered by vision-language models (VLMs) have significantly advanced human-computer interaction, enabling users to perform complex tasks through natural language instructions. However, these agents are vulnerable to context…
Stochastic multi-agent systems are a central modeling framework for autonomous controllers, communication protocols, and cyber-physical infrastructures. In many such systems, however, transition probabilities are only estimated from data…
As LLM agents transition to autonomous digital coworkers, maintaining deterministic goal-directedness in non-linear multi-turn conversations emerged as an architectural bottleneck. We identify and formalize a systemic failure mode termed…
In decision support systems, it is essential to get a candidate solution fast, even if it means resorting to an approximation. This constraint introduces a scalability requirement with regard to the kind of heuristics which can be used in…
Large Language Model (LLM)-empowered multi-agent systems extend the cognitive boundaries of individual agents through disciplined collaboration and interaction, while constructing these systems often requires labor-intensive manual designs.…
The rapid emergence of Large Language Models (LLMs) has catalyzed Agentic artificial intelligence (AI), autonomous systems integrating perception, reasoning, and action into closed-loop pipelines for continuous adaptation. While unlocking…
We introduce OfficeQA Pro, a benchmark for evaluating AI agents on grounded, multi-document reasoning over a large and heterogeneous document corpus. The corpus consists of U.S. Treasury Bulletins spanning nearly 100 years, comprising…
This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by…
The booming success of LLMs initiates rapid development in LLM agents. Though the foundation of an LLM agent is the generative model, it is critical to devise the optimal reasoning strategies and agent architectures. Accordingly, LLM agent…
Recent advances in Large Language Models (LLMs) have significantly improved table understanding tasks such as Table Question Answering (TableQA), yet challenges remain in ensuring reliability, scalability, and efficiency, especially in…
Reinforcement learning (RL) agents are often designed specifically for a particular problem and they generally have uninterpretable working processes. Statistical methods-based agent algorithms can be improved in terms of generalizability…
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…
Agentic frameworks are the software layer through which AI agents act in the world. Existing safety methods intervene on the model and therefore remain conditional on unverifiable properties of learned behavior. We introduce containment…
In an era where single large language models have dominated the landscape of artificial intelligence for years, multi-agent systems arise as new protagonists in conversational task-solving. While previous studies have showcased their…