Abstract--The emergence of Large Language Models (LLMs) is rapidly accelerating the development of autonomous multi-agent systems (MAS), paving the way for the Internet of Agents. However, traditional centralized MAS architectures present significant challenges, including single points of failure, vulnerability to censorship, inherent scalability limitations, and critical trust issues. We propose a novel Decentralized Multi-Agent System (DMAS) architecture designed to overcome these fundamental problems by enabling trust-aware, scalable, and censorship-resistant interactions among autonomous agents. Our DMAS features a decentralized agent runtime underpinned by a blockchain-based architecture. We formalize a trust-aware communication protocol that leverages cryptographic primitives and on-chain operations to provide security properties: verifiable interaction cycles, communication integrity, authenticity, non-repudiation, and conditional confidentiality, which we further substantiate through a comprehensive security analysis. The rapid advancements in Large Language Models (LLMs) [1]-[4] have opened unprecedented avenues for creating highly autonomous and intelligent agents. These LLM-augmented agents possess remarkable capabilities in understanding natural language, performing complex reasoning, planning intricate sequences of actions, and engaging in sophisticated communication.

With increased travelling needs more than ever, traffic congestion has become a major concern in most urban areas. Allocating spaces for on-street parking, further hinders traffic flow, by limiting the effective road width available for driving. With the advancement of vehicle-to-infrastructure connectivity technologies, we explore how the impact of on-street parking on traffic congestion could be minimized, by dynamically configuring on-street parking spaces. Towards that end, we formulate dynamic on-street parking space configuration as an optimization problem, and we follow a data driven approach, considering the nature of our problem. Our proposed solution comprises a two-layer multi agent reinforcement learning based framework, which is inherently scalable to large road networks. The lane level agents are responsible for deciding the optimal parking space configuration for each lane, and we introduce a novel Deep Q-learning architecture which effectively utilizes long short term memory networks and graph attention networks to capture the spatio-temporal correlations evident in the given problem. The block level agents control the actions of the lane level agents and maintain a sufficient level of parking around the block. We conduct a set of comprehensive experiments using SUMO, on both synthetic data as well as real-world data from the city of Melbourne. Our experiments show that the proposed framework could reduce the average travel time loss of vehicles significantly, reaching upto 47%, with a negligible increase in the walking distance for parking.

Recent large language models (LLMs) are trained on diverse corpora and tasks, leading them to develop complementary strengths. Multi-agent debate (MAD) has emerged as a popular way to leverage these strengths for robust reasoning, though it has mostly been applied to language-only tasks, leaving its efficacy on multimodal problems underexplored. In this paper, we study MAD for solving vision-and-language reasoning problems. Our setup enables generalizing the debate protocol with heterogeneous experts that possess single- and multi-modal capabilities. To this end, we present Weighted Iterative Society-of-Experts (WISE), a generalized and modular MAD framework that partitions the agents into Solvers, that generate solutions, and Reflectors, that verify correctness, assign weights, and provide natural language feedback. To aggregate the agents' solutions across debate rounds, while accounting for variance in their responses and the feedback weights, we present a modified Dawid-Skene algorithm for post-processing that integrates our two-stage debate model. We evaluate WISE on SMART-840, VisualPuzzles, EvoChart-QA, and a new SMART-840++ dataset with programmatically generated problem instances of controlled difficulty. Our results show that WISE consistently improves accuracy by 2-7% over the state-of-the-art MAD setups and aggregation methods across diverse multimodal tasks and LLM configurations.

With the advancement of natural language generation (NLG) technologies, creative story generation systems have gained increasing attention. However, current systems often fail to accurately translate user intent into satisfactory story outputs due to a lack of fine-grained control and unclear input specifications, limiting their applicability. To address this, we propose TaleFrame, a system that combines large language models (LLMs) with human-computer interaction (HCI) to generate stories through structured information, enabling precise control over the generation process. The innovation of TaleFrame lies in decomposing the story structure into four basic units: entities, events, relationships, and story outline. We leverage the Tinystories dataset, parsing and constructing a preference dataset consisting of 9,851 JSON-formatted entries, which is then used to fine-tune a local Llama model. By employing this JSON2Story approach, structured data is transformed into coherent stories. TaleFrame also offers an intuitive interface that supports users in creating and editing entities and events and generates stories through the structured framework. Users can control these units through simple interactions (e.g., drag-and-drop, attach, and connect), thus influencing the details and progression of the story. The generated stories can be evaluated across seven dimensions (e.g., creativity, structural integrity), with the system providing suggestions for refinement based on these evaluations. Users can iteratively adjust the story until a satisfactory result is achieved. Finally, we conduct quantitative evaluation and user studies that demonstrate the usefulness of TaleFrame. Dataset available at https://huggingface.co/datasets/guodaosun/tale-frame.

Reinforcement learning has become the dominant paradigm for eliciting reasoning and self-correction capabilities in large language models, but its computational expense motivates exploration of alternatives. Inspired by techniques from autonomous driving and robotics, we investigate whether supervised learning with synthetic error injection can induce self-correction abilities in language models. Our approach inserts artificial errors into reasoning chains, masks them, and supervises the model to recognize and correct these mistakes. Despite the intuitive appeal of this method, we find that it fails to significantly improve performance even on simple synthetic tasks across multiple models. Moreover, even when the model catches its own error, it often parrots the original mistake. We find that the distribution shift of synthetic errors to on-policy errors significantly degrades the error-correction capabilities of the fine-tuned model, even with good synthetic coverage of on-policy errors. Our results help explain why on-policy reinforcement learning methods have proven uniquely effective for eliciting self-correction.

This study explores the application of machine learning models, specifically a pretrained ResNet-50 model and a general SqueezeNet model, in diagnosing tuberculosis (TB) using chest X-ray images. TB, a persistent infectious disease affecting humanity for millennia, poses challenges in diagnosis, especially in resource-limited settings. Traditional methods, such as sputum smear microscopy and culture, are inefficient, prompting the exploration of advanced technologies like deep learning and computer vision. The study utilized a dataset from Kaggle, consisting of 4,200 chest X-rays, to develop and compare the performance of the two machine learning models. Preprocessing involved data splitting, augmentation, and resizing to enhance training efficiency. Evaluation metrics, including accuracy, precision, recall, and confusion matrix, were employed to assess model performance. Results showcase that the SqueezeNet achieved a loss of 32%, accuracy of 89%, precision of 98%, recall of 80%, and an F1 score of 87%. In contrast, the ResNet-50 model exhibited a loss of 54%, accuracy of 73%, precision of 88%, recall of 52%, and an F1 score of 65%. This study emphasizes the potential of machine learning in TB detection and possible implications for early identification and treatment initiation. The possibility of integrating such models into mobile devices expands their utility in areas lacking TB detection resources. However, despite promising results, the need for continued development of faster, smaller, and more accurate TB detection models remains crucial in contributing to the global efforts in combating TB.

Domain-specific question answering (QA) systems for services face unique challenges in integrating heterogeneous knowledge sources while ensuring both accuracy and safety. Existing large language models often struggle with factual consistency and context alignment in sensitive domains such as healthcare policies and government welfare. In this work, we introduce Knowledge-Aware Reasoning and Memory-Augmented Adaptation (KARMA), a novel framework designed to enhance QA performance in care scenarios. KARMA incorporates a dual-encoder architecture to fuse structured and unstructured knowledge sources, a gated memory unit to dynamically regulate external knowledge integration, and a safety-aware controllable decoder that mitigates unsafe outputs using safety classification and guided generation techniques. Extensive experiments on a proprietary QA dataset demonstrate that KARMA outperforms strong baselines in both answer quality and safety. This study offers a comprehensive solution for building trustworthy and adaptive QA systems in service contexts.

While visual data augmentation remains a cornerstone for training robust vision models, it has received limited attention in visual language models (VLMs), which predominantly rely on large-scale real data acquisition or synthetic diversity. Consequently, they may struggle with basic perception tasks that conventional models handle reliably. Given the substantial cost of pre-training and fine-tuning VLMs, continue training on augmented data yields limited and diminishing returns. In this paper, we present Visual Augmentation Chain-of-Thought (V ACoT), a framework that dynamically invokes image augmentations during model inference. By incorporating post-hoc transformations such as denoising, VACoT substantially improves robustness on challenging and out-of-distribution inputs, especially in OCR-related adversarial scenarios. Distinct from prior approaches limited to local cropping, VACoT integrates a structured collection of general visual augmentations, broadening the query image views while reducing training complexity and computational overhead with efficient agentic reinforcement learning. W e propose a conditional reward scheme that encourages necessary augmentation while penalizing verbose responses, ensuring concise and effective reasoning in perception tasks. W e demonstrate the superiority of VACoT with extensive experiments on 13 perception benchmarks and further introduce AdvOCR to highlight the generalization benefits of post-hoc visual augmentations in adversarial scenarios.

Optimizing numerical systems and mechanism design is crucial for enhancing player experience in Massively Multiplayer Online (MMO) games. Traditional optimization approaches rely on large-scale online experiments or parameter tuning over predefined statistical models, which are costly, time-consuming, and may disrupt player experience. Although simplified offline simulation systems are often adopted as alternatives, their limited fidelity prevents agents from accurately mimicking real player reasoning and reactions to interventions. To address these limitations, we propose a generative agent-based MMO simulation system empowered by Large Language Models (LLMs). By applying Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) on large-scale real player behavioral data, we adapt LLMs from general priors to game-specific domains, enabling realistic and interpretable player decision-making. In parallel, a data-driven environment model trained on real gameplay logs reconstructs dynamic in-game systems. Experiments demonstrate strong consistency with real-world player behaviors and plausible causal responses under interventions, providing a reliable, interpretable, and cost-efficient framework for data-driven numerical design optimization.

Offline Federated Reinforcement Learning (FRL), a marriage of federated learning and offline reinforcement learning, has attracted increasing interest recently. Albeit with some advancement, we find that the performance of most existing offline FRL methods drops dramatically when provided with mixed-quality data, that is, the logging behaviors (offline data) are collected by policies with varying qualities across clients. To overcome this limitation, this paper introduces a new vote-based offline FRL framework, named FOVA. It exploits a \emph{vote mechanism} to identify high-return actions during local policy evaluation, alleviating the negative effect of low-quality behaviors from diverse local learning policies. Besides, building on advantage-weighted regression (AWR), we construct consistent local and global training objectives, significantly enhancing the efficiency and stability of FOVA. Further, we conduct an extensive theoretical analysis and rigorously show that the policy learned by FOVA enjoys strict policy improvement over the behavioral policy. Extensive experiments corroborate the significant performance gains of our proposed algorithm over existing baselines on widely used benchmarks.