Costas Spanos

Junyu Guo, Shangding Gu, Ming Jin et al.

Large language models are increasingly used in settings where uncertainty must drive decisions such as abstention, retrieval, and verification. Most existing methods treat uncertainty as a latent quantity to estimate after generation rather than a signal the model is trained to express. We instead study uncertainty as an interface for control. We compare two complementary interfaces: a global interface, where the model verbalizes a calibrated confidence score for its final answer, and a local interface, where the model emits an explicit <uncertain> marker during reasoning when it enters a high-risk state. These interfaces provide different but complementary benefits. Verbalized confidence substantially improves calibration, reduces overconfident errors, and yields the strongest overall Adaptive RAG controller while using retrieval more selectively. Reasoning-time uncertainty signaling makes previously silent failures visible during generation, improves wrong-answer coverage, and provides an effective high-recall retrieval trigger. Our findings further show that the two interfaces work differently internally: verbal confidence mainly refines how existing uncertainty is decoded, whereas reasoning-time signaling induces a broader late-layer reorganization. Together, these results suggest that effective uncertainty in LLMs should be trained as task-matched communication: global confidence for deciding whether to trust a final answer, and local signals for deciding when intervention is needed.

Yingxuan Yang, Mulei Ma, Yuxuan Huang et al.

The emergence of AI agents powered by large language models (LLMs) marks a pivotal shift toward the Agentic Web, a new phase of the internet defined by autonomous, goal-driven interactions. In this paradigm, agents interact directly with one another to plan, coordinate, and execute complex tasks on behalf of users. This transition from human-driven to machine-to-machine interaction allows intent to be delegated, relieving users from routine digital operations and enabling a more interactive, automated web experience. In this paper, we present a structured framework for understanding and building the Agentic Web. We trace its evolution from the PC and Mobile Web eras and identify the core technological foundations that support this shift. Central to our framework is a conceptual model consisting of three key dimensions: intelligence, interaction, and economics. These dimensions collectively enable the capabilities of AI agents, such as retrieval, recommendation, planning, and collaboration. We analyze the architectural and infrastructural challenges involved in creating scalable agentic systems, including communication protocols, orchestration strategies, and emerging paradigms such as the Agent Attention Economy. We conclude by discussing the potential applications, societal risks, and governance issues posed by agentic systems, and outline research directions for developing open, secure, and intelligent ecosystems shaped by both human intent and autonomous agent behavior. A continuously updated collection of relevant studies for agentic web is available at: https://github.com/SafeRL-Lab/agentic-web.

Shangding Gu, Laixi Shi, Muning Wen et al.

Driven by inherent uncertainty and the sim-to-real gap, robust reinforcement learning (RL) seeks to improve resilience against the complexity and variability in agent-environment sequential interactions. Despite the existence of a large number of RL benchmarks, there is a lack of standardized benchmarks for robust RL. Current robust RL policies often focus on a specific type of uncertainty and are evaluated in distinct, one-off environments. In this work, we introduce Robust-Gymnasium, a unified modular benchmark designed for robust RL that supports a wide variety of disruptions across all key RL components-agents' observed state and reward, agents' actions, and the environment. Offering over sixty diverse task environments spanning control and robotics, safe RL, and multi-agent RL, it provides an open-source and user-friendly tool for the community to assess current methods and foster the development of robust RL algorithms. In addition, we benchmark existing standard and robust RL algorithms within this framework, uncovering significant deficiencies in each and offering new insights.

Shangding Gu, Xiaohan Wang, Donghao Ying et al.

Rapid advances in multimodal models demand benchmarks that rigorously evaluate understanding and reasoning in safety-critical, dynamic real-world settings. We present AccidentBench, a large-scale benchmark that combines vehicle accident scenarios with Beyond domains, safety-critical settings in air and water that emphasize spatial and temporal reasoning (e.g., navigation, orientation, multi-vehicle motion). The benchmark contains approximately 2000 videos and over 19000 human-annotated question--answer pairs spanning multiple video lengths (short/medium/long) and difficulty levels (easy/medium/hard). Tasks systematically probe core capabilities: temporal, spatial, and intent understanding and reasoning. By unifying accident-centric traffic scenes with broader safety-critical scenarios in air and water, AccidentBench offers a comprehensive, physically grounded testbed for evaluating models under real-world variability. Evaluations of state-of-the-art models (e.g., Gemini-2.5 Pro and GPT-5) show that even the strongest models achieve only about 18% accuracy on the hardest tasks and longest videos, revealing substantial gaps in real-world temporal, spatial, and intent reasoning. AccidentBench is designed to expose these critical gaps and drive the development of multimodal models that are safer, more robust, and better aligned with real-world safety-critical challenges. The code and dataset are available at: https://github.com/SafeRL-Lab/AccidentBench

Junyu Guo, Shangding Gu, Ming Jin et al.

The effectiveness of Large Language Models (LLMs) is heavily influenced by the reasoning strategies, or styles of thought, employed in their prompts. However, the interplay between these reasoning styles, model architecture, and task type remains poorly understood. To address this, we introduce StyleBench, a comprehensive benchmark for systematically evaluating reasoning styles across diverse tasks and models. We assess five representative reasoning styles, including Chain of Thought (CoT), Tree of Thought (ToT), Algorithm of Thought (AoT), Sketch of Thought (SoT), and Chain-of-Draft (CoD) on five reasoning tasks, using 15 open-source models from major families (LLaMA, Qwen, Mistral, Gemma, GPT-OSS, Phi, and DeepSeek) ranging from 270M to 120B parameters. Our large-scale analysis reveals that no single style is universally optimal. We demonstrate that strategy efficacy is highly contingent on both model scale and task type: search-based methods (AoT, ToT) excel in open-ended problems but require large-scale models, while concise styles (SoT, CoD) achieve radical efficiency gains on well-defined tasks. Furthermore, we identify key behavioral patterns: smaller models frequently fail to follow output instructions and default to guessing, while reasoning robustness emerges as a function of scale. Our findings offer a crucial roadmap for selecting optimal reasoning strategies based on specific constraints, we open source the benchmark in https://github.com/JamesJunyuGuo/Style_Bench.

Doseok Jang, Larry Yan, Lucas Spangher et al.

Reinforcement learning (RL) is a powerful tool for optimal control that has found great success in Atari games, the game of Go, robotic control, and building optimization. RL is also very brittle; agents often overfit to their training environment and fail to generalize to new settings. Unsupervised environment design (UED) has been proposed as a solution to this problem, in which the agent trains in environments that have been specially selected to help it learn. Previous UED algorithms focus on trying to train an RL agent that generalizes across a large distribution of environments. This is not necessarily desirable when we wish to prioritize performance in one environment over others. In this work, we will be examining the setting of robust RL building control, where we wish to train an RL agent that prioritizes performing well in normal weather while still being robust to extreme weather conditions. We demonstrate a novel UED algorithm, ActivePLR, that uses uncertainty-aware neural network architectures to generate new training environments at the limit of the RL agent's ability while being able to prioritize performance in a desired base environment. We show that ActivePLR is able to outperform state-of-the-art UED algorithms in minimizing energy usage while maximizing occupant comfort in the setting of building control.

Shangding Gu, Donghao Ying, Ming Jin et al. · berkeley

We introduce Model Feedback Learning (MFL), a novel test-time optimization framework for optimizing inputs to pre-trained AI models or deployed hardware systems without requiring any retraining of the models or modifications to the hardware. In contrast to existing methods that rely on adjusting model parameters, MFL leverages a lightweight reverse model to iteratively search for optimal inputs, enabling efficient adaptation to new objectives under deployment constraints. This framework is particularly advantageous in real-world settings, such as semiconductor manufacturing recipe generation, where modifying deployed systems is often infeasible or cost-prohibitive. We validate MFL on semiconductor plasma etching tasks, where it achieves target recipe generation in just five iterations, significantly outperforming both Bayesian optimization and human experts. Beyond semiconductor applications, MFL also demonstrates strong performance in chemical processes (e.g., chemical vapor deposition) and electronic systems (e.g., wire bonding), highlighting its broad applicability. Additionally, MFL incorporates stability-aware optimization, enhancing robustness to process variations and surpassing conventional supervised learning and random search methods in high-dimensional control settings. By enabling few-shot adaptation, MFL provides a scalable and efficient paradigm for deploying intelligent control in real-world environments.

Josip Josifovski, Shangding Gu, Mohammadhossein Malmir et al.

Domain randomization has emerged as a fundamental technique in reinforcement learning (RL) to facilitate the transfer of policies from simulation to real-world robotic applications. Many existing domain randomization approaches have been proposed to improve robustness and sim2real transfer. These approaches rely on wide randomization ranges to compensate for the unknown actual system parameters, leading to robust but inefficient real-world policies. In addition, the policies pretrained in the domain-randomized simulation are fixed after deployment due to the inherent instability of the optimization processes based on RL and the necessity of sampling exploitative but potentially unsafe actions on the real system. This limits the adaptability of the deployed policy to the inevitably changing system parameters or environment dynamics over time. We leverage safe RL and continual learning under domain-randomized simulation to address these limitations and enable safe deployment-time policy adaptation in real-world robot control. The experiments show that our method enables the policy to adapt and fit to the current domain distribution and environment dynamics of the real system while minimizing safety risks and avoiding issues like catastrophic forgetting of the general policy found in randomized simulation during the pretraining phase. Videos and supplementary material are available at https://safe-cda.github.io/.

Junyu Guo, Zhi Zheng, Donghao Ying et al. · berkeley

Constrained reinforcement learning (RL) seeks high-performance policies under safety constraints. We focus on an offline setting where the agent has only a fixed dataset -- common in realistic tasks to prevent unsafe exploration. To address this, we propose Diffusion-Regularized Constrained Offline Reinforcement Learning (DRCORL), which first uses a diffusion model to capture the behavioral policy from offline data and then extracts a simplified policy to enable efficient inference. We further apply gradient manipulation for safety adaptation, balancing the reward objective and constraint satisfaction. This approach leverages high-quality offline data while incorporating safety requirements. Empirical results show that DRCORL achieves reliable safety performance, fast inference, and strong reward outcomes across robot learning tasks. Compared to existing safe offline RL methods, it consistently meets cost limits and performs well with the same hyperparameters, indicating practical applicability in real-world scenarios.

William Arnold, Tarang Srivastava, Lucas Spangher et al.

Optimizing prices for energy demand response requires a flexible controller with ability to navigate complex environments. We propose a reinforcement learning controller with surprise minimizing modifications in its architecture. We suggest that surprise minimization can be used to improve learning speed, taking advantage of predictability in peoples' energy usage. Our architecture performs well in a simulation of energy demand response. We propose this modification to improve functionality and save in a large scale experiment.

Doseok Jang, Lucas Spangher, Manan Khattar et al.

Our team is proposing to run a full-scale energy demand response experiment in an office building. Although this is an exciting endeavor which will provide value to the community, collecting training data for the reinforcement learning agent is costly and will be limited. In this work, we examine how offline training can be leveraged to minimize data costs (accelerate convergence) and program implementation costs. We present two approaches to doing so: pretraining our model to warm start the experiment with simulated tasks, and using a planning model trained to simulate the real world's rewards to the agent. We present results that demonstrate the utility of offline reinforcement learning to efficient price-setting in the energy demand response problem.

Doseok Jang, Lucas Spangher, Manan Khattar et al.

Our team is proposing to run a full-scale energy demand response experiment in an office building. Although this is an exciting endeavor which will provide value to the community, collecting training data for the reinforcement learning agent is costly and will be limited. In this work, we apply a meta-learning architecture to warm start the experiment with simulated tasks, to increase sample efficiency. We present results that demonstrate a similar a step up in complexity still corresponds with better learning.

Ioannis C. Konstantakopoulos, Kristy A. Hamilton, Yashaswini Murthy et al.

As Internet of Things (IoT) technologies are increasingly being deployed, situations frequently arise where multiple stakeholders must reconcile preferences to control a shared resource. We perform a 5-month long experiment dubbed 'smartSDH' (carried out in 27 employees' office space) where users report their preferences for the brightness of overhead lighting. smartSDH implements a modified Vickrey-Clarke-Groves (VCG) mechanism; assuming users are rational, it incentivizes truthful reporting, implements the socially desirable outcome, and compensates participants to ensure higher payoffs under smartSDH when compared with the default outside option(i.e., the option chosen in the absence of such a mechanism). smartSDH assesses the feasibility of the VCG mechanism in the context of smart building control and evaluated smartSDH's effect using metrics such as light level satisfaction, incentive satisfaction, and energy consumption. Although previous studies on the theoretical aspects of the mechanism indicate user satisfaction, our experiments indicate quite the contrary. We found that the participants were significantly less satisfied with light brightness and incentives determined by the VCG mechanism over time. These data suggest the need for more realistic behavioral models to design IoT technologies and highlights difficulties in estimating preferences from observable external factors such as atmospheric conditions.

Ruoxi Jia, David Dao, Boxin Wang et al.

"How much is my data worth?" is an increasingly common question posed by organizations and individuals alike. An answer to this question could allow, for instance, fairly distributing profits among multiple data contributors and determining prospective compensation when data breaches happen. In this paper, we study the problem of data valuation by utilizing the Shapley value, a popular notion of value which originated in coopoerative game theory. The Shapley value defines a unique payoff scheme that satisfies many desiderata for the notion of data value. However, the Shapley value often requires exponential time to compute. To meet this challenge, we propose a repertoire of efficient algorithms for approximating the Shapley value. We also demonstrate the value of each training instance for various benchmark datasets.

Jingkang Wang, Ruoxi Jia, Gerald Friedland et al.

Despite the great success achieved in machine learning (ML), adversarial examples have caused concerns with regards to its trustworthiness: A small perturbation of an input results in an arbitrary failure of an otherwise seemingly well-trained ML model. While studies are being conducted to discover the intrinsic properties of adversarial examples, such as their transferability and universality, there is insufficient theoretic analysis to help understand the phenomenon in a way that can influence the design process of ML experiments. In this paper, we deduce an information-theoretic model which explains adversarial attacks as the abuse of feature redundancies in ML algorithms. We prove that feature redundancy is a necessary condition for the existence of adversarial examples. Our model helps to explain some major questions raised in many anecdotal studies on adversarial examples. Our theory is backed up by empirical measurements of the information content of benign and adversarial examples on both image and text datasets. Our measurements show that typical adversarial examples introduce just enough redundancy to overflow the decision making of an ML model trained on corresponding benign examples. We conclude with actionable recommendations to improve the robustness of machine learners against adversarial examples.

Ioannis C. Konstantakopoulos, Andrew R. Barkan, Shiying He et al.

The implementation of smart building technology in the form of smart infrastructure applications has great potential to improve sustainability and energy efficiency by leveraging humans-in-the-loop strategy. However, human preference in regard to living conditions is usually unknown and heterogeneous in its manifestation as control inputs to a building. Furthermore, the occupants of a building typically lack the independent motivation necessary to contribute to and play a key role in the control of smart building infrastructure. Moreover, true human actions and their integration with sensing/actuation platforms remains unknown to the decision maker tasked with improving operational efficiency. By modeling user interaction as a sequential discrete game between non-cooperative players, we introduce a gamification approach for supporting user engagement and integration in a human-centric cyber-physical system. We propose the design and implementation of a large-scale network game with the goal of improving the energy efficiency of a building through the utilization of cutting-edge Internet of Things (IoT) sensors and cyber-physical systems sensing/actuation platforms. A benchmark utility learning framework that employs robust estimations for classical discrete choice models provided for the derived high dimensional imbalanced data. To improve forecasting performance, we extend the benchmark utility learning scheme by leveraging Deep Learning end-to-end training with Deep bi-directional Recurrent Neural Networks. We apply the proposed methods to high dimensional data from a social game experiment designed to encourage energy efficient behavior among smart building occupants in Nanyang Technological University (NTU) residential housing. Using occupant-retrieved actions for resources such as lighting and A/C, we simulate the game defined by the estimated utility functions.

Ming Jin, Andreas Damianou, Pieter Abbeel et al.

We propose a new approach to inverse reinforcement learning (IRL) based on the deep Gaussian process (deep GP) model, which is capable of learning complicated reward structures with few demonstrations. Our model stacks multiple latent GP layers to learn abstract representations of the state feature space, which is linked to the demonstrations through the Maximum Entropy learning framework. Incorporating the IRL engine into the nonlinear latent structure renders existing deep GP inference approaches intractable. To tackle this, we develop a non-standard variational approximation framework which extends previous inference schemes. This allows for approximate Bayesian treatment of the feature space and guards against overfitting. Carrying out representation and inverse reinforcement learning simultaneously within our model outperforms state-of-the-art approaches, as we demonstrate with experiments on standard benchmarks ("object world","highway driving") and a new benchmark ("binary world").

Ming Jin, Ruoxi Jia, Zhoayi Kang et al.

Non-intrusive presence detection of individuals in commercial buildings is much easier to implement than intrusive methods such as passive infrared, acoustic sensors, and camera. Individual power consumption, while providing useful feedback and motivation for energy saving, can be used as a valuable source for presence detection. We conduct pilot experiments in an office setting to collect individual presence data by ultrasonic sensors, acceleration sensors, and WiFi access points, in addition to the individual power monitoring data. PresenceSense (PS), a semi-supervised learning algorithm based on power measurement that trains itself with only unlabeled data, is proposed, analyzed and evaluated in the study. Without any labeling efforts, which are usually tedious and time consuming, PresenceSense outperforms popular models whose parameters are optimized over a large training set. The results are interpreted and potential applications of PresenceSense on other data sources are discussed. The significance of this study attaches to space security, occupancy behavior modeling, and energy saving of plug loads.