Large language models (LLMs) now mediate many web-based mental-health, crisis, and other emotionally sensitive services, yet their psychosocial safety in these settings remains poorly understood and weakly evaluated. We present DialogGuard, a multi-agent framework for assessing psychosocial risks in LLM-generated responses along five high-severity dimensions: privacy violations, discriminatory behaviour, mental manipulation, psychological harm, and insulting behaviour. DialogGuard can be applied to diverse generative models through four LLM-as-a-judge pipelines, including single-agent scoring, dual-agent correction, multi-agent debate, and stochastic majority voting, grounded in a shared three-level rubric usable by both human annotators and LLM judges. Using PKU-SafeRLHF with human safety annotations, we show that multi-agent mechanisms detect psychosocial risks more accurately than non-LLM baselines and single-agent judging; dual-agent correction and majority voting provide the best trade-off between accuracy, alignment with human ratings, and robustness, while debate attains higher recall but over-flags borderline cases. We release Dialog-Guard as open-source software with a web interface that provides per-dimension risk scores and explainable natural-language rationales. A formative study with 12 practitioners illustrates how it supports prompt design, auditing, and supervision of web-facing applications for vulnerable users.

LLM-based trading agents are increasingly deployed in real-world financial markets to perform autonomous analysis and execution. However, their reliability and robustness under adversarial or faulty conditions remain largely unexamined, despite operating in high-risk, irreversible financial environments. We propose TradeTrap, a unified evaluation framework for systematically stress-testing both adaptive and procedural autonomous trading agents. TradeTrap targets four core components of autonomous trading agents: market intelligence, strategy formulation, portfolio and ledger handling, and trade execution, and evaluates their robustness under controlled system-level perturbations. All evaluations are conducted in a closed-loop historical backtesting setting on real US equity market data with identical initial conditions, enabling fair and reproducible comparisons across agents and attacks. Extensive experiments show that small perturbations at a single component can propagate through the agent decision loop and induce extreme concentration, runaway exposure, and large portfolio drawdowns across both agent types, demonstrating that current autonomous trading agents can be systematically misled at the system level. Our code is available at https://github.com/Yanlewen/TradeTrap.

The financial market is a mission-critical playground for AI agents due to its temporal dynamics and low signal-to-noise ratio. Building an effective algorithmic trading system may require a professional team to develop and test over the years. In this paper, we propose an orchestration framework for financial agents, which aims to democratize financial intelligence to the general public. We map each component of the traditional algorithmic trading system to agents, including planner, orchestrator, alpha agents, risk agents, portfolio agents, backtest agents, execution agents, audit agents, and memory agent. We present two in-house trading examples. For the stock trading task (hourly data from 04/2024 to 12/2024), our approach achieved a return of $20.42\%$, a Sharpe ratio of 2.63, and a maximum drawdown of $-3.59\%$, while the S&P 500 index yielded a return of $15.97\%$. For the BTC trading task (minute data from 27/07/2025 to 13/08/2025), our approach achieved a return of $8.39\%$, a Sharpe ratio of $0.38$, and a maximum drawdown of $-2.80\%$, whereas the BTC price increased by $3.80\%$. Our code is available on \href{https://github.com/Open-Finance-Lab/AgenticTrading}{GitHub}.

Fast, efficient, robust communication during wildfire and other emergency responses is critical. One way to achieve this is by coordinating swarms of autonomous aerial vehicles carrying communications equipment to form an ad-hoc network connecting emergency response personnel to both each other and central command. However, operating in such extreme environments may lead to individual networking agents being damaged or rendered inoperable, which could bring down the network and interrupt communications. To overcome this challenge and enable multi-agent UAV networking in difficult environments, this paper introduces and formalizes the problem of Robust Task Networking Under Attrition (RTNUA), which extends connectivity maintenance in multi-robot systems to explicitly address proactive redundancy and attrition recovery. We introduce Physics-Informed Robust Employment of Multi-Agent Networks ($Φ$IREMAN), a topological algorithm leveraging physics-inspired potential fields to solve this problem. Through simulation across 25 problem configurations, $Φ$IREMAN consistently outperforms the DCCRS baseline, and on large-scale problems with up to 100 tasks and 500 drones, maintains $>99.9\%$ task uptime despite substantial attrition, demonstrating both effectiveness and scalability.

Abstract--The deployment of autonomous AI agents in Internet of Things (IoT) energy systems requires decision-making mechanisms that remain robust, efficient, and trustworthy under real-time constraints and imperfect monitoring. While reinforcement learning enables adaptive prosumer behaviors, ensuring economic consistency and preventing strategic manipulation remain open challenges, particularly when sensing noise or partial observability degrades the operator's ability to verify actions. This paper introduces a trust-enforcement framework for IoT energy trading that combines an α-approximate Vick-rey-Clarke-Groves (VCG) double auction with an immediate one-shot penalty. Unlike reputation-or history-based approaches, the proposed mechanism restores truthful reporting within a single round, even when allocation accuracy is approximate and monitoring is noisy. We theoretically characterize the incentive gap induced by approximation and derive a penalty threshold that guarantees truthful bidding under bounded sensing errors. T o evaluate learning-enabled prosumers, we embed the mechanism into a multi-agent reinforcement learning environment reflecting stochastic generation, dynamic loads, and heterogeneous trading opportunities. Experiments show that improved allocation accuracy consistently reduces deviation incentives, the required penalty matches analytical predictions, and learned bidding behaviors remain stable and interpretable despite imperfect monitoring. These results demonstrate that lightweight penalty designs can reliably align strategic IoT agents with socially efficient energy-trading outcomes. The rapid expansion of the Internet of Things (IoT) has created large-scale networks of heterogeneous sensors, distributed devices, and autonomous software agents that must jointly perceive, reason, and act in dynamic cyber-physical environments. X. Shao and R. Shimizu are with the Department of Electrical and Electronic Information Engineering, Toyohashi University of Technology, Toyohashi, Aichi 441-8580, Japan (e-mail: xun.shao@tut.jp).

Double perovskites (DPs) are promising candidates for sustainable energy technologies due to their compositional tunability and compatibility with low-energy fabrication, yet their vast design space poses a major challenge for conditional materials discovery. This work introduces a multi-agent, text gradient-driven framework that performs DP composition generation under natural-language conditions by integrating three complementary feedback sources: LLM-based self-evaluation, DP-specific domain knowledge-informed feedback, and ML surrogate-based feedback. Analogous to how knowledge-informed machine learning improves the reliability of conventional data-driven models, our framework incorporates domain-informed text gradients to guide the generative process toward physically meaningful regions of the DP composition space. Systematic comparison of three incremental configurations, (i) pure LLM generation, (ii) LLM generation with LLM reasoning-based feedback, and (iii) LLM generation with domain knowledge-guided feedback, shows that iterative guidance from knowledge-informed gradients improves stability-condition satisfaction without additional training data, achieving over 98% compositional validity and up to 54% stable or metastable candidates, surpassing both the LLM-only baseline (43%) and prior GAN-based results (27%). Analyses of ML-based gradients further reveal that they enhance performance in in-distribution (ID) regions but become unreliable in out-of-distribution (OOD) regimes. Overall, this work provides the first systematic analysis of multi-agent, knowledge-guided text gradients for DP discovery and establishes a generalizable blueprint for MAS-driven generative materials design aimed at advancing sustainable technologies.

Large Language Model (LLM) agent systems have advanced rapidly, driven by their strong generalization in zero-shot settings. To further enhance reasoning and accuracy on complex tasks, Multi-Agent Debate (MAD) has emerged as a promising framework that engages multiple LLM agents in structured debates to encourage diverse reasoning. However, triggering MAD for every query is inefficient, as it incurs substantial computational (token) cost and may even degrade accuracy by overturning correct single-agent answers. To address these limitations, we propose intelligent Multi-Agent Debate (iMAD), a token-efficient framework that selectively triggers MAD only when it is likely to be beneficial (i.e., correcting an initially wrong answer). To achieve this goal, iMAD learns generalizable model behaviors to make accurate debate decisions. Specifically, iMAD first prompts a single agent to produce a structured self-critique response, from which we extract 41 interpretable linguistic and semantic features capturing hesitation cues. Then, iMAD uses a lightweight debate-decision classifier, trained using our proposed FocusCal loss, to determine whether to trigger MAD, enabling robust debate decisions without test dataset-specific tuning. Through extensive experiments using six (visual) question answering datasets against five competitive baselines, we have shown that iMAD significantly reduces token usage (by up to 92%) while also improving final answer accuracy (by up to 13.5%).

Large transformer models, trained on diverse datasets, have demonstrated impressive few-shot performance on previously unseen tasks without requiring parameter updates. This capability has also been explored in Reinforcement Learning (RL), where agents interact with the environment to retrieve context and maximize cumulative rewards, showcasing strong adaptability in complex settings. However, in cooperative Multi-Agent Reinforcement Learning (MARL), where agents must coordinate toward a shared goal, decentralized policy deployment can lead to mismatches in task alignment and reward assignment, limiting the efficiency of policy adaptation. To address this challenge, we introduce Multi-agent In-context Coordination via Decentralized Memory Retrieval (MAICC), a novel approach designed to enhance coordination by fast adaptation. Our method involves training a centralized embedding model to capture fine-grained trajectory representations, followed by decentralized models that approximate the centralized one to obtain team-level task information. Based on the learned embeddings, relevant trajectories are retrieved as context, which, combined with the agents' current sub-trajectories, inform decision-making. During decentralized execution, we introduce a novel memory mechanism that effectively balances test-time online data with offline memory. Based on the constructed memory, we propose a hybrid utility score that incorporates both individual- and team-level returns, ensuring credit assignment across agents. Extensive experiments on cooperative MARL benchmarks, including Level-Based Foraging (LBF) and SMAC (v1/v2), show that MAICC enables faster adaptation to unseen tasks compared to existing methods. Code is available at https://github.com/LAMDA-RL/MAICC.

Academic advising is critical to student success in higher education, yet high student-to-advisor ratios limit advisors' capacity to provide timely support, particularly during peak periods. Recent advances in Large Language Models (LLMs) present opportunities to enhance the advising process. We present AdvisingWise, a multi-agent system that automates time-consuming tasks, such as information retrieval and response drafting, while preserving human oversight. AdvisingWise leverages authoritative institutional resources and adaptively prompts students about their academic backgrounds to generate reliable, personalized responses. All system responses undergo human advisor validation before delivery to students. We evaluate AdvisingWise through a mixed-methods approach: (1) expert evaluation on responses of 20 sample queries, (2) LLM-as-a-judge evaluation of the information retrieval strategy, and (3) a user study with 8 academic advisors to assess the system's practical utility. Our evaluation shows that AdvisingWise produces accurate, personalized responses. Advisors reported increasingly positive perceptions after using AdvisingWise, as their initial concerns about reliability and personalization diminished. We conclude by discussing the implications of human-AI synergy on the practice of academic advising.

Developing large language models (LLMs) to cooperate and compete effectively within multi-agent systems (MASs) is a critical step towards more advanced intelligence. While reinforcement learning (RL) has proven effective for enhancing reasoning in single-agent tasks, its extension to multi-turn, multi-agent scenarios remains underexplored due to the challenges of long-horizon credit assignment and agent-specific advantage estimation. To address these challenges, we introduce MARSHAL, an end-to-end RL framework that incentivizes Multi-Agent Reasoning through Self-play witH strAtegic LLMs in both cooperative and competitive games. MARSHAL features a turn-level advantage estimator that aligns learning signals with each interaction for credit assignment, and an agent-specific advantage normalization to stabilize multi-agent training. By learning with self-play across cooperative and competitive games, MARSHAL agent trained from Qwen3-4B develops strong strategic abilities that generalize to held-out games with up to 28.7% performance improvements. More importantly, the capability acquired through self-play generalizes beyond games, yielding consistent performance gains of MASs in reasoning benchmarks. When integrated into leading MASs, our MARSHAL agent achieves significant performance gains of up to 10.0% on AIME, 6.6% on GPQA-Diamond, and 3.5% on average across all benchmarks. These results establish end-to-end RL training with self-play in strategic games as a powerful approach for developing generalizable multi-agent reasoning capabilities in LLMs.