Related papers: Agentic Observability: Automated Alert Triage for …
Modern enterprise AI applications increasingly rely on compound AI systems - architectures that compose multiple models, retrievers, and tools to accomplish complex tasks. Deploying such systems in production demands inference…
This paper presents a temporal expression language for monitoring AI agent behavior, enabling systematic error-detection of LLM-based agentic systems that exhibit variable outputs due to stochastic generation processes. Drawing from…
Agentic AI workflows (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low. A promising solution is inference-time alignment, which uses extra compute at test time to…
Automated Program Repair (APR) agents leverage Large Language Models (LLMs) to autonomously diagnose and fix software bugs through reasoning, planning, and tool use. Despite impressive leaderboard gains on benchmarks such as SWE-bench,…
Language agents have demonstrated autonomous decision-making abilities by reasoning with foundation models. Recently, efforts have been made to train language agents for performance improvement, with multi-step reasoning and action…
Automatic extraction of product attribute values is an important enabling technology in e-Commerce platforms. This task is usually modeled using sequence labeling architectures, with several extensions to handle multi-attribute extraction.…
When language model agents tackle complex software engineering tasks, they often degrade over long trajectories, which we define as *agent drift*. We focus on two recurring failure modes *overthinking* and *overacting*, i.e., where the…
While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after explicit user prompts. This paradigm ignores a critical opportunity: the idle time between…
System logs play a critical role in maintaining the reliability of software systems. Fruitful studies have explored automatic log-based anomaly detection and achieved notable accuracy on benchmark datasets. However, when applied to…
As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions,…
Artificial intelligence (AI) has been increasingly applied to the condition monitoring of vehicular equipment, aiming to enhance maintenance strategies, reduce costs, and improve safety. Leveraging the edge computing paradigm, AI-based…
This technical brief introduces Deep Agent, an advanced autonomous AI system designed to manage complex multi-phase tasks through a novel hierarchical task management architecture. The system's foundation is built on our Hierarchical Task…
Powerful autonomous systems, which reason, plan, and converse using and between numerous tools and agents, are made possible by Large Language Models (LLMs), Vision-Language Models (VLMs), and new agentic AI systems, like LangChain and…
Marketing and product personalisation provide a prominent and visible use-case for the application of Information Retrieval methods across several business domains. Recently, agentic approaches to these problems have been gaining traction.…
We propose a novel mechanism for real-time (human-in-the-loop) feedback focused on false positive reduction to enhance anomaly detection models. It was designed for the lightweight deployment of a behavioral network anomaly detection model.…
We present a method of endowing agents in an agent-based model (ABM) with sophisticated cognitive capabilities and a naturally tunable level of intelligence. Often, ABMs use random behavior or greedy algorithms for maximizing objectives…
Environments built for people are increasingly operated by a new class of economic actors: LLM-powered software agents making decisions on our behalf. These decisions range from our purchases to travel plans to medical treatment selection.…
This paper proposes a highly robust autonomous agent framework based on the ReAct paradigm, designed to solve complex tasks through adaptive decision making and multi-agent collaboration. Unlike traditional frameworks that rely on fixed…
AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy tool outputs. We address this gap by manually annotating failed agent runs and release a…
Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, play a substantial role in many cutting-edge commercial applications, and continue to fascinate researchers across fields for…