The rapid advancement of Large Language Models (LLMs) has significantly enhanced the capabilities of Multi-Agent Systems (MAS) in supporting humans with complex, real-world tasks. However, MAS still face challenges in effective task planning when handling highly complex tasks with uncertainty, often resulting in misleading or incorrect outputs that hinder task execution. To address this, we propose XAgents, a unified multi-agent cooperative framework built on a multipolar task processing graph and IF-THEN rules. XAgents uses the multipolar task processing graph to enable dynamic task planning and handle task uncertainty. During subtask processing, it integrates domain-specific IF-THEN rules to constrain agent behaviors, while global rules enhance inter-agent collaboration. We evaluate the performance of XAgents across three distinct datasets, demonstrating that it consistently surpasses state-of-the-art single-agent and multi-agent approaches in both knowledge-typed and logic-typed question-answering tasks. The codes for XAgents are available at: https://github.com/AGI-FHBC/XAgents.

Visual Question Answering (VQA) has been a popular task that combines vision and language, with numerous relevant implementations in literature. Even though there are some attempts that approach explainability and robustness issues in VQA models, very few of them employ counterfactuals as a means of probing such challenges in a model-agnostic way. In this work, we propose a systematic method for explaining the behavior and investigating the robustness of VQA models through counterfactual perturbations. For this reason, we exploit structured knowledge bases to perform deterministic, optimal and controllable word-level replacements targeting the linguistic modality, and we then evaluate the model's response against such counterfactual inputs. Finally, we qualitatively extract local and global explanations based on counterfactual responses, which are ultimately proven insightful towards interpreting VQA model behaviors. By performing a variety of perturbation types, targeting different parts of speech of the input question, we gain insights to the reasoning of the model, through the comparison of its responses in different adversarial circumstances. Overall, we reveal possible biases in the decision-making process of the model, as well as expected and unexpected patterns, which impact its performance quantitatively and qualitatively, as indicated by our analysis.

Distributed fuzzy neural networks (DFNNs) have attracted increasing attention recently due to their learning abilities in handling data uncertainties in distributed scenarios. However, it is challenging for DFNNs to handle cases in which the local data are non-independent and identically distributed (non-IID). In this paper, we propose a federated fuzzy neural network (FedFNN) with evolutionary rule learning (ERL) to cope with non-IID issues as well as data uncertainties. The FedFNN maintains a global set of rules in a server and a personalized subset of these rules for each local client. ERL is inspired by the theory of biological evolution; it encourages rule variations while activating superior rules and deactivating inferior rules for local clients with non-IID data. Specifically, ERL consists of two stages in an iterative procedure: a rule cooperation stage that updates global rules by aggregating local rules based on their activation statuses and a rule evolution stage that evolves the global rules and updates the activation statuses of the local rules. This procedure improves both the generalization and personalization of the FedFNN for dealing with non-IID issues and data uncertainties. Extensive experiments conducted on a range of datasets demonstrate the superiority of the FedFNN over state-of-the-art methods.

Secretary of State Antony Blinken said Tuesday that the US will seek worldwide regulations on how to prevent the misuse of artificial intelligence, as he reinforced threats against Russia over hacking. The top US diplomat expressed concern at a conference on emerging technologies that an increasing number of authoritarian nations, led by China, are utilizing the internet and new technology to suppress dissent and establish greater control. "As a result, the world is at a crossroads. And we must choose between abandoning our vision for the internet and intensifying our struggle. Blinken stated, "We will intensify our fight."

Meanwhile, China's surveillance firms continue to expand globally as China aims to be the world leader in artificial intelligence by 2030. Nadella said regulation "does have a real place here," particularly rules at the "time of use" of AI, like facial recognition. "I think we should be thinking a lot harder around regulation at the time of use. Because facial recognition or object recognition by itself is not good or bad; it is just a technology. So we have to be able to sort of even think about regulation more at the run time, more at the design time," Nadella said.

For consumer companies, large-scale leveraging of customer and behavioral data to drive personalized customer experiences is turning into a virtual arms race. Marketing technology platforms of the last 10 years were built around campaign process that were still highly manual, requiring marketing execs to do all the testing, optimization and which makes the cycle time for learning and actually influencing marketing very slow. Now more and more marketers recognize the need to deploy advanced personalization capabilities that make the use of machine-learned optimization. And, Matt Fleckenstein, Chief Product Officer at Amplero, helps marketers achieve just that. With a track record for conceiving, building, and launching martech products and services it comes easy to him.

We consider rules for discarding predictors in lasso regression and related problems, for computational efficiency. El Ghaoui et al (2010) propose "SAFE" rules that guarantee that a coefficient will be zero in the solution, based on the inner products of each predictor with the outcome. In this paper we propose strong rules that are not foolproof but rarely fail in practice. These can be complemented with simple checks of the Karush- Kuhn-Tucker (KKT) conditions to provide safe rules that offer substantial speed and space savings in a variety of statistical convex optimization problems.