We introduce FinDebate, a multi-agent framework for financial analysis, integrating collaborative debate with domain-specific Retrieval-Augmented Generation (RAG). Five specialized agents, covering earnings, market, sentiment, valuation, and risk, run in parallel to synthesize evidence into multi-dimensional insights. To mitigate overconfidence and improve reliability, we introduce a safe debate protocol that enables agents to challenge and refine initial conclusions while preserving coherent recommendations. Experimental results, based on both LLM-based and human evaluations, demonstrate the framework's efficacy in producing high-quality analysis with calibrated confidence levels and actionable investment strategies across multiple time horizons.

Automating radiology report generation poses a dual challenge: building clinically reliable systems and designing rigorous evaluation protocols. We introduce a multi-agent reinforcement learning framework that serves as both a benchmark and evaluation environment for multimodal clinical reasoning in the radiology ecosystem. The proposed framework integrates large language models (LLMs) and large vision models (LVMs) within a modular architecture composed of ten specialized agents responsible for image analysis, feature extraction, report generation, review, and evaluation. This design enables fine-grained assessment at both the agent level (e.g., detection and segmentation accuracy) and the consensus level (e.g., report quality and clinical relevance). We demonstrate an implementation using chatGPT-4o on public radiology datasets, where LLMs act as evaluators alongside medical radiologist feedback. By aligning evaluation protocols with the LLM development lifecycle, including pretraining, finetuning, alignment, and deployment, the proposed benchmark establishes a path toward trustworthy deviance-based radiology report generation.

As the industry increasingly adopts agentic AI systems, understanding their unique vulnerabilities becomes critical. Prior research suggests that security flaws at the model level do not fully capture the risks present in agentic deployments, where models interact with tools and external environments. This paper investigates this gap by conducting a comparative red teaming analysis of GPT-OSS-20B, a 20-billion parameter open-source model. Using our observability framework AgentSeer to deconstruct agentic systems into granular actions and components, we apply iterative red teaming attacks with harmful objectives from HarmBench at two distinct levels: the standalone model and the model operating within an agentic loop. Our evaluation reveals fundamental differences between model level and agentic level vulnerability profiles. Critically, we discover the existence of agentic-only vulnerabilities, attack vectors that emerge exclusively within agentic execution contexts while remaining inert against standalone models. Agentic level iterative attacks successfully compromise objectives that completely failed at the model level, with tool-calling contexts showing 24\% higher vulnerability than non-tool contexts. Conversely, certain model-specific exploits work exclusively at the model level and fail when transferred to agentic contexts, demonstrating that standalone model vulnerabilities do not always generalize to deployed systems.

Abstract--We propose MADP, a novel diffusion-model-based approach for collaboration in decentralized robot swarms. MADP leverages diffusion models to generate samples from complex and high-dimensional action distributions that capture the interdependencies between agents' actions. Each robot conditions policy sampling on a fused representation of its own observations and perceptual embeddings received from peers. T o evaluate this approach, we task a team of holonomic robots piloted by MADP to address coverage control--a canonical multi agent navigation problem. The policy is trained via imitation learning from a clairvoyant expert on the coverage control problem, with the diffusion process parameterized by a spatial transformer architecture to enable decentralized inference. We evaluate the system under varying numbers, locations, and variances of importance density functions, capturing the robustness demands of real-world coverage tasks. Experiments demonstrate that our model inherits valuable properties from diffusion models, generalizing across agent densities and environments, and consistently outperforming state-of-the-art baselines.

Systematic Literature Reviews (SLRs) are foundational to evidence-based research but remain labor-intensive and prone to inconsistency across disciplines. We present an LLM-based SLR evaluation copilot built on a Multi-Agent System (MAS) architecture to assist researchers in assessing the overall quality of the systematic literature reviews. The system automates protocol validation, methodological assessment, and topic relevance checks using a scholarly database. Unlike conventional single-agent methods, our design integrates a specialized agentic approach aligned with PRISMA guidelines to support more structured and interpretable evaluations. We conducted an initial study on five published SLRs from diverse domains, comparing system outputs to expert-annotated PRISMA scores, and observed 84% agreement. While early results are promising, this work represents a first step toward scalable and accurate NLP-driven systems for interdisciplinary workflows and reveals their capacity for rigorous, domain-agnostic knowledge aggregation to streamline the review process.

This article presents a novel multi-agent spatial transformer (MAST) for learning communication policies in large-scale decentralized and collaborative multi-robot systems (DC-MRS). Challenges in collaboration in DC-MRS arise from: (i) partial observable states as robots make only localized perception, (ii) limited communication range with no central server, and (iii) independent execution of actions. The robots need to optimize a common task-specific objective, which, under the restricted setting, must be done using a communication policy that exhibits the desired collaborative behavior. The proposed MAST is a decentralized transformer architecture that learns communication policies to compute abstract information to be shared with other agents and processes the received information with the robot's own observations. The MAST extends the standard transformer with new positional encoding strategies and attention operations that employ windowing to limit the receptive field for MRS. These are designed for local computation, shift-equivariance, and permutation equivariance, making it a promising approach for DC-MRS. We demonstrate the efficacy of MAST on decentralized assignment and navigation (DAN) and decentralized coverage control. Efficiently trained using imitation learning in a centralized setting, the decentralized MAST policy is robust to communication delays, scales to large teams, and performs better than the baselines and other learning-based approaches.

Thematic Analysis (TA) is a widely used qualitative method that provides a structured yet flexible framework for identifying and reporting patterns in clinical interview transcripts. However, manual thematic analysis is time-consuming and limits scalability. Recent advances in LLMs offer a pathway to automate thematic analysis, but alignment with human results remains limited. To address these limitations, we propose SFT-TA, an automated thematic analysis framework that embeds supervised fine-tuned (SFT) agents within a multi-agent system. Our framework outperforms existing frameworks and the gpt-4o baseline in alignment with human reference themes. We observed that SFT agents alone may underperform, but achieve better results than the baseline when embedded within a multi-agent system. Our results highlight that embedding SFT agents in specific roles within a multi-agent system is a promising pathway to improve alignment with desired outputs for thematic analysis.

Collaborative perception aims to extend sensing coverage and improve perception accuracy by sharing information among multiple agents. However, due to differences in viewpoints and spatial positions, agents often acquire heterogeneous observations. Existing intermediate fusion methods primarily focus on aligning similar features, often overlooking the perceptual diversity among agents. To address this limitation, we propose CoBEVMoE, a novel collaborative perception framework that operates in the Bird's Eye View (BEV) space and incorporates a Dynamic Mixture-of-Experts (DMoE) architecture. In DMoE, each expert is dynamically generated based on the input features of a specific agent, enabling it to extract distinctive and reliable cues while attending to shared semantics. This design allows the fusion process to explicitly model both feature similarity and heterogeneity across agents. Furthermore, we introduce a Dynamic Expert Metric Loss (DEML) to enhance inter-expert diversity and improve the discriminability of the fused representation. Extensive experiments on the OPV2V and DAIR-V2X-C datasets demonstrate that CoBEVMoE achieves state-of-the-art performance. Specifically, it improves the IoU for Camera-based BEV segmentation by +1.5% on OPV2V and the AP@50 for LiDAR-based 3D object detection by +3.0% on DAIR-V2X-C, verifying the effectiveness of expert-based heterogeneous feature modeling in multi-agent collaborative perception. The source code will be made publicly available at https://github.com/godk0509/CoBEVMoE.

Accurate trajectory prediction and motion planning are crucial for autonomous driving systems to navigate safely in complex, interactive environments characterized by multimodal uncertainties. However, current generation-then-evaluation frameworks typically construct multiple plausible trajectory hypotheses but ultimately adopt a single most likely outcome, leading to overconfident decisions and a lack of fallback strategies that are vital for safety in rare but critical scenarios. Moreover, the usual decoupling of prediction and planning modules could result in socially inconsistent or unrealistic joint trajectories, especially in highly interactive traffic. To address these challenges, we propose a contingency-aware diffusion planner (CoPlanner), a unified framework that jointly models multi-agent interactive trajectory generation and contingency-aware motion planning. Specifically, the pivot-conditioned diffusion mechanism anchors trajectory sampling on a validated, shared short-term segment to preserve temporal consistency, while stochastically generating diverse long-horizon branches that capture multimodal motion evolutions. In parallel, we design a contingency-aware multi-scenario scoring strategy that evaluates candidate ego trajectories across multiple plausible long-horizon evolution scenarios, balancing safety, progress, and comfort. This integrated design preserves feasible fallback options and enhances robustness under uncertainty, leading to more realistic interaction-aware planning. Extensive closed-loop experiments on the nuPlan benchmark demonstrate that CoPlanner consistently surpasses state-of-the-art methods on both Val14 and Test14 datasets, achieving significant improvements in safety and comfort under both reactive and non-reactive settings. Code and model will be made publicly available upon acceptance.

The advancement of foundation models fosters new initiatives for policy learning in achieving safe and efficient autonomous driving. However, a critical bottleneck lies in the manual engineering of reward functions and training curricula for complex and dynamic driving tasks, which is a labor-intensive and time-consuming process. To address this problem, we propose OGR (Orchestrate, Generate, Reflect), a novel automated driving policy learning framework that leverages vision-language model (VLM)-based multi-agent collaboration. Our framework capitalizes on advanced reasoning and multimodal understanding capabilities of VLMs to construct a hierarchical agent system. Specifically, a centralized orchestrator plans high-level training objectives, while a generation module employs a two-step analyze-then-generate process for efficient generation of reward-curriculum pairs. A reflection module then facilitates iterative optimization based on the online evaluation. Furthermore, a dedicated memory module endows the VLM agents with the capabilities of long-term memory. To enhance robustness and diversity of the generation process, we introduce a parallel generation scheme and a human-in-the-loop technique for augmentation of the reward observation space. Through efficient multi-agent cooperation and leveraging rich multimodal information, OGR enables the online evolution of reinforcement learning policies to acquire interaction-aware driving skills. Extensive experiments in the CARLA simulator demonstrate the superior performance, robust generalizability across distinct urban scenarios, and strong compatibility with various RL algorithms. Further real-world experiments highlight the practical viability and effectiveness of our framework. The source code will be available upon acceptance of the paper.