Related papers: TRACER: Trajectory Risk Aggregation for Critical E…

Code agents are advancing rapidly, but debugging them is becoming increasingly difficult. As frameworks orchestrate parallel tool calls and multi-stage workflows over complex tasks, making the agent's state transitions and error propagation…

Trajectory prediction, the task of forecasting future agent behavior from past data, is central to safe and efficient autonomous driving. A diverse set of methods (e.g., rule-based or learned with different architectures and datasets) have…

To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail remains a critical challenge. In three user studies on a…

Navigating complex urban environments safely is a key to realize fully autonomous systems. Predicting future locations of vulnerable road users, such as pedestrians and cyclists, thus, has received a lot of attention in the recent years.…

Language-model agents increasingly emit uncertainty signals throughout a trajectory, but existing agentic UQ evaluations often conflate ranking usefulness with probabilistic truthfulness. AUROC, AUPRC, risk-coverage, Trajectory ECE, and…

We present an openly documented methodology for fine-tuning language models to detect temporal attack patterns in multi-agent AI workflows using OpenTelemetry trace analysis. We curate a dataset of 80,851 examples from 18 public…

Despite rapid progress in building conversational AI agents, robustness is still largely untested. Small shifts in user behavior, such as being more impatient, incoherent, or skeptical, can cause sharp drops in agent performance, revealing…

Robust adversarial reinforcement learning has emerged as an effective paradigm for training agents to handle uncertain disturbance in real environments, with critical applications in sequential decision-making domains such as autonomous…

Understanding the behavior of software in execution is a key step in identifying and fixing performance issues. This is especially important in high performance computing contexts where even minor performance tweaks can translate into large…

Agentic applications based on large language models increasingly rely on multi-step interaction loops involving planning, action execution, and environment feedback. While such systems are now deployed at scale, improving them…

The central challenge in robotic manipulation of deformable objects lies in aligning high-level semantic instructions with physical interaction points under complex appearance and texture variations. Due to near-infinite degrees of freedom,…

Uncertainty modeling is critical in trajectory forecasting systems for both interpretation and safety reasons. To better predict the future trajectories of multiple agents, recent works have introduced interaction modules to capture…

LLM-driven GUI agents are increasingly used in production systems to automate workflows and simulate users for evaluation and optimization. Yet most GUI-agent evaluations emphasize task success and provide limited evidence on whether agents…

Agentic AI systems act through tools and evolve their behavior over long, stochastic interaction traces. This setting complicates assurance, because behavior depends on nondeterministic environments and probabilistic model outputs. Prior…

AI control protocols use monitors to detect attacks by untrusted AI agents, but standard single-score monitors face two limitations: they miss subtle attacks where outputs look clean but reasoning is off, and they collapse to near-zero…

Testing conversational AI systems at scale across diverse domains necessitates realistic and diverse user interactions capturing a wide array of behavioral patterns. We present a novel multi-agent framework for realistic, explainable human…

Complex interactions among agents present a significant challenge for autonomous driving in real-world scenarios. Recently, a promising approach has emerged, which formulates the interactions of agents as a level-k game framework. It…

This work presents a new sufficient condition for synthesizing nonlinear controllers that yield bounded closed-loop tracking error transients despite the presence of unmatched uncertainties that are concurrently being learned online. The…

As Reinforcement Learning (RL) agents are increasingly deployed in real-world applications, ensuring their behavior is transparent and trustworthy is paramount. A key component of trust is explainability, yet much of the work in Explainable…

Test-time scaling improves the reasoning performance of large language models but often results in token-inefficient overthinking, where models continue reasoning beyond what is necessary for a correct answer. Existing dynamic early-exit…