Autonomous agents capable of planning, reasoning, and executing actions on the web offer a promising avenue for automating computer tasks. However, the majority of existing benchmarks primarily focus on text-based agents, neglecting many natural tasks that require visual information to effectively solve. Given that most computer interfaces cater to human perception, visual information often augments textual data in ways that text-only models struggle to harness effectively. To bridge this gap, we introduce VisualWebArena, a benchmark designed to assess the performance of multimodal web agents on realistic \textit{visually grounded tasks}. VisualWebArena comprises of a set of diverse and complex web-based tasks that evaluate various capabilities of autonomous multimodal agents. To perform on this benchmark, agents need to accurately process image-text inputs, interpret natural language instructions, and execute actions on websites to accomplish user-defined objectives. We conduct an extensive evaluation of state-of-the-art LLM-based autonomous agents, including several multimodal models. Through extensive quantitative and qualitative analysis, we identify several limitations of text-only LLM agents, and reveal gaps in the capabilities of state-of-the-art multimodal language agents. VisualWebArena provides a framework for evaluating multimodal autonomous language agents, and offers insights towards building stronger autonomous agents for the web. Our code, baseline models, and data is publicly available at https://jykoh.com/vwa.

In the past year, MultiModal Large Language Models (MM-LLMs) have undergone substantial advancements, augmenting off-the-shelf LLMs to support MM inputs or outputs via cost-effective training strategies. The resulting models not only preserve the inherent reasoning and decision-making capabilities of LLMs but also empower a diverse range of MM tasks. In this paper, we provide a comprehensive survey aimed at facilitating further research of MM-LLMs. Specifically, we first outline general design formulations for model architecture and training pipeline. Subsequently, we provide brief introductions of $26$ existing MM-LLMs, each characterized by its specific formulations. Additionally, we review the performance of MM-LLMs on mainstream benchmarks and summarize key training recipes to enhance the potency of MM-LLMs. Lastly, we explore promising directions for MM-LLMs while concurrently maintaining a real-time tracking website for the latest developments in the field. We hope that this survey contributes to the ongoing advancement of the MM-LLMs domain.

Intelligent robot is the ultimate goal in the robotics field. Existing works leverage learning-based or optimization-based methods to accomplish human-defined tasks. However, the challenge of enabling robots to explore various environments autonomously remains unresolved. In this work, we propose a framework named GExp, which enables robots to explore and learn autonomously without human intervention. To achieve this goal, we devise modules including self-exploration, knowledge-base-building, and close-loop feedback based on foundation models. Inspired by the way that infants interact with the world, GExp encourages robots to understand and explore the environment with a series of self-generated tasks. During the process of exploration, the robot will acquire skills from beneficial experiences that are useful in the future. GExp provides robots with the ability to solve complex tasks through self-exploration. GExp work is independent of prior interactive knowledge and human intervention, allowing it to adapt directly to different scenarios, unlike previous studies that provided in-context examples as few-shot learning. In addition, we propose a workflow of deploying the real-world robot system with self-learned skills as an embodied assistant.

In the rapidly advancing field of multi-agent systems, ensuring robustness in unfamiliar and adversarial settings is crucial. Notwithstanding their outstanding performance in familiar environments, these systems often falter in new situations due to overfitting during the training phase. This is especially pronounced in settings where both cooperative and competitive behaviours are present, encapsulating a dual nature of overfitting and generalisation challenges. To address this issue, we present Multi-Agent Diagnostics for Robustness via Illuminated Diversity (MADRID), a novel approach for generating diverse adversarial scenarios that expose strategic vulnerabilities in pre-trained multi-agent policies. Leveraging the concepts from open-ended learning, MADRID navigates the vast space of adversarial settings, employing a target policy's regret to gauge the vulnerabilities of these settings. We evaluate the effectiveness of MADRID on the 11vs11 version of Google Research Football, one of the most complex environments for multi-agent reinforcement learning. Specifically, we employ MADRID for generating a diverse array of adversarial settings for TiZero, the state-of-the-art approach which "masters" the game through 45 days of training on a large-scale distributed infrastructure. We expose key shortcomings in TiZero's tactical decision-making, underlining the crucial importance of rigorous evaluation in multi-agent systems.

Machine-learning methods are gradually being adopted in a great variety of social, economic, and scientific contexts, yet they are notorious for struggling with exact mathematics. A typical example is computer algebra, which includes tasks like simplifying mathematical terms, calculating formal derivatives, or finding exact solutions of algebraic equations. Traditional software packages for these purposes are commonly based on a huge database of rules for how a specific operation (e.g., differentiation) transforms a certain term (e.g., sine function) into another one (e.g., cosine function). Thus far, these rules have usually needed to be discovered and subsequently programmed by humans. Focusing on the paradigmatic example of solving linear equations in symbolic form, we demonstrate how the process of finding elementary transformation rules and step-by-step solutions can be automated using reinforcement learning with deep neural networks.

Data protection legislation like the European Union's General Data Protection Regulation (GDPR) establishes the \textit{right to be forgotten}: a user (client) can request contributions made using their data to be removed from learned models. In this paper, we study how to remove the contributions made by a client participating in a Federated Online Learning to Rank (FOLTR) system. In a FOLTR system, a ranker is learned by aggregating local updates to the global ranking model. Local updates are learned in an online manner at a client-level using queries and implicit interactions that have occurred within that specific client. By doing so, each client's local data is not shared with other clients or with a centralised search service, while at the same time clients can benefit from an effective global ranking model learned from contributions of each client in the federation. In this paper, we study an effective and efficient unlearning method that can remove a client's contribution without compromising the overall ranker effectiveness and without needing to retrain the global ranker from scratch. A key challenge is how to measure whether the model has unlearned the contributions from the client $c^*$ that has requested removal. For this, we instruct $c^*$ to perform a poisoning attack (add noise to this client updates) and then we measure whether the impact of the attack is lessened when the unlearning process has taken place. Through experiments on four datasets, we demonstrate the effectiveness and efficiency of the unlearning strategy under different combinations of parameter settings.

Perception occurs when two individuals interpret the same information differently. Despite being a known phenomenon with implications for bias in decision-making, as individuals' experience determines interpretation, perception remains largely overlooked in automated decision-making (ADM) systems. In particular, it can have considerable effects on the fairness or fair usage of an ADM system, as fairness itself is context-specific and its interpretation dependent on who is judging. In this work, we formalize perception under causal reasoning to capture the act of interpretation by an individual. We also formalize individual experience as additional causal knowledge that comes with and is used by an individual. Further, we define and discuss loaded attributes, which are attributes prone to evoke perception. Sensitive attributes, such as gender and race, are clear examples of loaded attributes. We define two kinds of causal perception, unfaithful and inconsistent, based on the causal properties of faithfulness and consistency. We illustrate our framework through a series of decision-making examples and discuss relevant fairness applications. The goal of this work is to position perception as a parameter of interest, useful for extending the standard, single interpretation ADM problem formulation.

Artificial Intelligence (AI) finds widespread applications across various domains, sparking concerns about fairness in its deployment. While fairness in AI remains a central concern, the prevailing discourse often emphasizes outcome-based metrics without a nuanced consideration of the differential impacts within subgroups. Bias mitigation techniques do not only affect the ranking of pairs of instances across sensitive groups, but often also significantly affect the ranking of instances within these groups. Such changes are hard to explain and raise concerns regarding the validity of the intervention. Unfortunately, these effects largely remain under the radar in the accuracy-fairness evaluation framework that is usually applied. This paper challenges the prevailing metrics for assessing bias mitigation techniques, arguing that they do not take into account the changes within-groups and that the resulting prediction labels fall short of reflecting real-world scenarios. We propose a paradigm shift: initially, we should focus on generating the most precise ranking for each subgroup. Following this, individuals should be chosen from these rankings to meet both fairness standards and practical considerations.

Approaching robotic cloth manipulation using reinforcement learning based on visual feedback is appealing as robot perception and control can be learned simultaneously. However, major challenges result due to the intricate dynamics of cloth and the high dimensionality of the corresponding states, what shadows the practicality of the idea. To tackle these issues, we propose TraKDis, a novel Transformer-based Knowledge Distillation approach that decomposes the visual reinforcement learning problem into two distinct stages. In the first stage, a privileged agent is trained, which possesses complete knowledge of the cloth state information. This privileged agent acts as a teacher, providing valuable guidance and training signals for subsequent stages. The second stage involves a knowledge distillation procedure, where the knowledge acquired by the privileged agent is transferred to a vision-based agent by leveraging pre-trained state estimation and weight initialization. TraKDis demonstrates better performance when compared to state-of-the-art RL techniques, showing a higher performance of 21.9%, 13.8%, and 8.3% in cloth folding tasks in simulation. Furthermore, to validate robustness, we evaluate the agent in a noisy environment; the results indicate its ability to handle and adapt to environmental uncertainties effectively. Real robot experiments are also conducted to showcase the efficiency of our method in real-world scenarios.

Recent advancements in AI have led to the development of large multimodal models (LMMs) capable of processing complex tasks involving joint reasoning over text and visual content in the image (e.g., navigating maps in public places). This paper introduces ConTextual, a novel benchmark comprising instructions designed explicitly to evaluate LMMs' ability to perform context-sensitive text-rich visual reasoning. ConTextual emphasizes diverse real-world scenarios (e.g., time-reading, navigation, shopping and more) demanding a deeper understanding of the interactions between textual and visual elements. Our findings reveal a significant performance gap of 30.8% between the best-performing LMM, GPT-4V(ision), and human capabilities using human evaluation indicating substantial room for improvement in context-sensitive text-rich visual reasoning. Notably, while GPT-4V excelled in abstract categories like meme and quote interpretation, its overall performance still lagged behind humans. In addition to human evaluations, we also employed automatic evaluation metrics using GPT-4, uncovering similar trends in performance disparities. We also perform a fine-grained evaluation across diverse visual contexts and provide qualitative analysis which provides a robust framework for future advancements in the LMM design. https://con-textual.github.io/