Related papers: Do Agents Know What They Can't Do? Evaluating Feas…
Video production workflows offer a rich and demanding arena for evaluating multimodal AI agents: they require composite capabilities across text, image, audio, and video understanding, along with long-horizon planning, and tool use. To this…
A multiagent sequential decision problem has been seen in many critical applications including urban transportation, autonomous driving cars, military operations, etc. Its widely known solution, namely multiagent reinforcement learning, has…
One of the main research areas in Artificial Intelligence is the coding of agents (programs) which are able to learn by themselves in any situation. This means that agents must be useful for purposes other than those they were created for,…
This paper presents a solution to the automatic task planning problem for multi-agent systems. A formal framework is developed based on the Nondeterministic Finite Automata with $\epsilon$-transitions, where given the capabilities,…
The problem of assigning agents to tasks is a central computational challenge in many multi-agent autonomous systems. However, in the real world, agents are not always perfect and may fail due to a number of reasons. A motivating…
Autonomous agent systems powered by Large Language Models (LLMs) have demonstrated promising capabilities in automating complex tasks. However, current evaluations largely rely on success rates without systematically analyzing the…
Agentic AI systems are increasingly being integrated into scientific workflows, yet their behavior under realistic conditions remains insufficiently understood. We evaluate CMBAgent across two workflow paradigms and eighteen astrophysical…
Mixed-integer optimization problems arise in a wide range of control applications. Benders decomposition is a widely used algorithm for solving such problems by decomposing them into a mixed-integer master problem and a continuous…
Dynamic game theory is an increasingly popular tool for modeling multi-agent, e.g. human-robot, interactions. Game-theoretic models presume that each agent wishes to minimize a private cost function that depends on others' actions. These…
The deployment of agent systems in an enterprise environment is often hindered by several challenges: common models lack domain-specific process knowledge, leading to disorganized plans, missing key tools, and poor execution stability. To…
This paper develops a stochastic programming framework for multi-agent systems where task decomposition, assignment, and scheduling problems are simultaneously optimized. The framework can be applied to heterogeneous mobile robot teams with…
LLM-based multi-agent systems can fail even when planned actions are executed correctly because agents may misjudge their knowledge when evaluating plan feasibility, a phenomenon we term epistemic miscalibration in planning. Unlike…
While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions. Unlike mathematical reasoning where errors are often rectifiable via backtracking, tool-use failures frequently induce…
Tool-using large language model (LLM) agents often face a fundamental tension between answer quality and execution cost. Fixed workflows are stable but inflexible, while free-form multi-step reasoning methods such as ReAct may improve task…
Automating a production line with robotic arms is a complex, demanding task that requires not only substantial resources but also a deep understanding of the automated processes and available technologies and tools. Expert integrators must…
Through multi-agent competition, the simple objective of hide-and-seek, and standard reinforcement learning algorithms at scale, we find that agents create a self-supervised autocurriculum inducing multiple distinct rounds of emergent…
Since Artificial Intelligence (AI) software uses techniques like deep lookahead search and stochastic optimization of huge neural networks to fit mammoth datasets, it often results in complex behavior that is difficult for people to…
While current Computer Use Agent (CUA) benchmarks measure task completion effectively, they provide limited assessment of enterprise deployment readiness, emphasizing functional correctness over the operational reliability required for…
As machine learning systems become more powerful they also become increasingly unpredictable and opaque. Yet, finding human-understandable explanations of how they work is essential for their safe deployment. This technical report…
Agent benchmarks typically report only final outcomes: pass or fail. This threatens evaluation credibility in three ways. First, scores may be inflated or deflated by shortcuts and benchmark artifacts, misrepresenting capability. Second,…