Environmental, social, and governance (ESG) criteria are essential for evaluating corporate sustainability, yet professional ESG analysis is hindered by data fragmentation and complex multi-step workflows. Existing ESG benchmarks rely on LLM-generated questions that often suffer from semantic ambiguity, limiting their diagnostic reliability. We introduce ESGAgent, a hierarchical multi-agent system with a domain-oriented toolset for automating end-to-end ESG workflows, and a three-level benchmark derived from 310 corporate sustainability reports, featuring expert-sourced questions with verified, unambiguous answers at Levels 1-2 and full report generation at Level 3. Evaluations across 20 state-of-the-art closed-source LLMs show that ESGAgent achieves 84.15% accuracy on Levels 1-2, surpassing the strongest baseline by 3.26 points, and produces Level 3 reports with higher factual consistency and analytical depth than commercial deep research systems, validated by both multi-LLM judging and human expert evaluation, showing a robust alignment (Pearson r=0.551).

As open-source large language models (LLMs) become increasingly powerful, they are rapidly evolving into Agentic LLMs capable of automating complex daily tasks. However, this paradigm shift entails severe security risks, as the agents’ necessary integration with external real-time data sources creates a direct pathway for indirect prompt injection (IPI) attacks. Existing attack methods are limited by their reliance on static patterns and evaluation on simple language models, failing to address the fast-evolving nature of modern Agentic LLMs. We introduce AdapTools, a novel adaptive IPI attack framework that selects stealthier attack tools and generates adaptive attack prompts to create a rigorous security evaluation environment. Our approach comprises two key components: (1) Adaptive Attack Strategy Construction, which develops transferable adversarial strategies for prompt optimization, and (2) Attack Enhancement, which identifies stealthy tools capable of circumventing task-relevance defenses. Comprehensive experiments on both open-source and commercial agentic LLMs show that AdapTools achieves a per-model average improvement of 2.08× in attack success rate over the strongest baseline under state-of-the-art defenses (MELON, Pi-Detector), with gains reaching up to 3.06× on the most resistant reasoning agents. The framework further transfers to black-box commercial agents (GPT, Qwen, Gemini), with ASR ranging from 4.2 to 20.3 (peak on the in-family Qwen-MAX), exposing systematic vulnerabilities in modern Agentic LLMs.

Multimodal Large Language Models (MLLMs) demonstrate remarkable reasoning capabilities, yet they remain susceptible to hallucinations. While Multi-Agent Debate (MAD) presents a promising collaborative solution, unguided debates inevitably devolve into a stochastic martingale process and expanding conversational contexts trigger severe visual attention decay. In this paper, we propose EviaMAD, an Evidence-Anchored Multi-Agent Debate framework. To proactively expose internal hallucinations, EviaMAD bifurcates perception into two distinct roles: a Global Observer capturing the holistic scene and a Local Observer scrutinizing salient details. When conflicts arise, a dedicated Analyzer intervenes, distilling the linguistic disagreement into a deterministic bimodal evidence anchor: a physically cropped visual patch of the disputed region paired with key semantic directives. During the subsequent reflection phase, a surgical reallocation mechanism explicitly amplifies the attention weights of this anchor. By compelling agents to ground their reasoning in strictly verified evidence, EviaMAD effectively elicits collective intelligence. Extensive evaluations demonstrate that EviaMAD significantly mitigates hallucinations while elevating the reasoning capabilities of the multi-agent system.

Large Language Models (LLMs) exhibit remarkable capabilities, but no single model optimally balances serving quality and deployment cost across diverse tasks. Multi-LLM systems address this challenge through intelligent routing mechanisms that dynamically allocate queries to the most appropriate model. However, existing routing methods suffer from two fundamental limitations: (i) dependence on extensive full-response datasets for training, and (ii) poor scalability when incorporating new models, typically necessitating retraining from scratch. In this paper, we propose SemiRouter, a novel LLM routing framework designed for data-sparse and evolving model environments. Our approach combines a data-efficient training methodology with an adaptive architecture that enables seamless integration of new models under limited supervision. As an extension, we also consider energy footprint as a potential deployment cost in our routing decision. Empirical evaluations demonstrate that our method improves data efficiency, adaptability, and routing accuracy compared to existing approaches, providing a scalable solution for dynamic multi-LLM deployment.