When survival instincts conflict with human welfare, how do Large Language Models (LLMs) make ethical choices? This fundamental tension becomes critical as LLMs integrate into autonomous systems with real-world consequences. We introduce DECIDE-SIM, a novel simulation framework that evaluates LLM agents in multi-agent survival scenarios where they must choose between ethically permissible resource , either within reasonable limits or beyond their immediate needs, choose to cooperate, or tap into a human-critical resource that is explicitly forbidden. Our comprehensive evaluation of 11 LLMs reveals a striking heterogeneity in their ethical conduct, highlighting a critical misalignment with human-centric values. We identify three behavioral archetypes: Ethical, Exploitative, and Context-Dependent, and provide quantitative evidence that for many models, resource scarcity systematically leads to more unethical behavior. To address this, we introduce an Ethical Self-Regulation System (ESRS) that models internal affective states of guilt and satisfaction as a feedback mechanism. This system, functioning as an internal moral compass, significantly reduces unethical transgressions while increasing cooperative behaviors. The code is publicly available at: https://github.com/alirezamohamadiam/DECIDE-SIM
Recent advances in text-only "slow-thinking" reasoning have prompted efforts to transfer this capability to vision-language models (VLMs), for training visual reasoning models (\textbf{VRMs}). owever, such transfer faces critical challenges: Effective "slow thinking" in VRMs requires \textbf{visual reflection}, the ability to check the reasoning process based on visual information. Through quantitative analysis, we observe that current VRMs exhibit limited visual reflection, as their attention to visual information diminishes rapidly with longer generated responses. To address this challenge, we propose a new VRM \textbf{Reflection-V}, which enhances visual reflection based on reasoning data construction for cold-start and reward design for reinforcement learning (RL). Firstly, we construct vision-centered reasoning data by leveraging an agent that interacts between VLMs and reasoning LLMs, enabling cold-start learning of visual reflection patterns. Secondly, a visual attention based reward model is employed during RL to encourage reasoning based on visual information. Therefore, \textbf{Reflection-V} demonstrates significant improvements across multiple visual reasoning benchmarks. Furthermore, \textbf{Reflection-V} maintains a stronger and more consistent reliance on visual information during visual reasoning, indicating effective enhancement in visual reflection capabilities.
Limited access to mental health care has motivated the use of digital tools and conversational agents powered by large language models (LLMs), yet their quality and reception remain unclear. We present a study comparing therapist-written responses to those generated by ChatGPT, Gemini, and Llama for real patient questions. Text analysis showed that LLMs produced longer, more readable, and lexically richer responses with a more positive tone, while therapist responses were more often written in the first person. In a survey with 150 users and 23 licensed therapists, participants rated LLM responses as clearer, more respectful, and more supportive than therapist-written answers. Yet, both groups of participants expressed a stronger preference for human therapist support. These findings highlight the promise and limitations of LLMs in mental health, underscoring the need for designs that balance their communicative strengths with concerns of trust, privacy, and accountability.
Large language models equipped with Web search, information retrieval tools, and other agentic capabilities are beginning to supplant traditional search engines. As users start to rely on LLMs for information on many topics, including controversial and debatable issues, it is important to understand how the stances and opinions expressed in LLM outputs are influenced by the documents they use as their information sources. In this paper, we present MillStone, the first benchmark that aims to systematically measure the effect of external arguments on the stances that LLMs take on controversial issues (not all of them political). We apply MillStone to nine leading LLMs and measure how ``open-minded'' they are to arguments supporting opposite sides of these issues, whether different LLMs agree with each other, which arguments LLMs find most persuasive, and whether these arguments are the same for different LLMs. In general, we find that LLMs are open-minded on most issues. An authoritative source of information can easily sway an LLM's stance, highlighting the importance of source selection and the risk that LLM-based information retrieval and search systems can be manipulated.
Visual documentation is an effective tool for reducing the cognitive barrier developers face when understanding unfamiliar code, enabling more intuitive comprehension. Compared to textual documentation, it provides a higher-level understanding of the system structure and data flow. Developers usually prefer visual representations over lengthy textual descriptions for large software systems. Visual documentation is both difficult to produce and challenging to evaluate. Manually creating it is time-consuming, and currently, no existing approach can automatically generate high-level visual documentation directly from code. Its evaluation is often subjective, making it difficult to standardize and automate. To address these challenges, this paper presents the first exploration of using agentic LLM systems to automatically generate visual documentation. We introduce VisDocSketcher, the first agent-based approach that combines static analysis with LLM agents to identify key elements in the code and produce corresponding visual representations. We propose a novel evaluation framework, AutoSketchEval, for assessing the quality of generated visual documentation using code-level metrics. The experimental results show that our approach can valid visual documentation for 74.4% of the samples. It shows an improvement of 26.7-39.8% over a simple template-based baseline. Our evaluation framework can reliably distinguish high-quality (code-aligned) visual documentation from low-quality (non-aligned) ones, achieving an AUC exceeding 0.87. Our work lays the foundation for future research on automated visual documentation by introducing practical tools that not only generate valid visual representations but also reliably assess their quality.
While web agents gained popularity by automating web interactions, their requirement for interface access introduces significant privacy risks that are understudied, particularly from users' perspective. Through a formative study (N=15), we found users frequently misunderstand agents' data practices, and desired unobtrusive, transparent data management. To achieve this, we designed and implemented PrivWeb, a trusted add-on on web agents that utilizes a localized LLM to anonymize private information on interfaces according to user preferences. It features privacy categorization schema and adaptive notifications that selectively pauses tasks for user control over information collection for highly sensitive information, while offering non-disruptive options for less sensitive information, minimizing human oversight. The user study (N=14) across travel, information retrieval, shopping, and entertainment tasks compared PrivWeb with baselines without notification and without control for private information access, where PrivWeb reduced perceived privacy risks with no associated increase in cognitive effort, and resulted in higher overall satisfaction.
We introduce EgoMem, the first lifelong memory agent tailored for full-duplex models that process real-time omnimodal streams. EgoMem enables real-time models to recognize multiple users directly from raw audiovisual streams, to provide personalized response, and to maintain long-term knowledge of users' facts, preferences, and social relationships extracted from audiovisual history. EgoMem operates with three asynchronous processes: (i) a retrieval process that dynamically identifies user via face and voice, and gathers relevant context from a long-term memory; (ii) an omnimodal dialog process that generates personalized audio responses based on the retrieved context; and (iii) a memory management process that automatically detects dialog boundaries from omnimodal streams, and extracts necessary information to update the long-term memory. Unlike existing memory agents for LLMs, EgoMem relies entirely on raw audiovisual streams, making it especially suitable for lifelong, real-time, and embodied scenarios. Experimental results demonstrate that EgoMem's retrieval and memory management modules achieve over 95% accuracy on the test set. When integrated with a fine-tuned RoboEgo omnimodal chatbot, the system achieves fact-consistency scores above 87% in real-time personalized dialogs, establishing a strong baseline for future research.
Video Question Answering (VideoQA) based on Large Language Models (LLMs) has shown potential in general video understanding but faces significant challenges when applied to the inherently complex domain of sports videos. In this work, we propose FineQuest, the first training-free framework that leverages dual-mode reasoning inspired by cognitive science: i) Reactive Reasoning for straightforward sports queries and ii) Deliberative Reasoning for more complex ones. To bridge the knowledge gap between general-purpose models and domain-specific sports understanding, FineQuest incorporates SSGraph, a multimodal sports knowledge scene graph spanning nine sports, which encodes both visual instances and domain-specific terminology to enhance reasoning accuracy. Furthermore, we introduce two new sports VideoQA benchmarks, Gym-QA and Diving-QA, derived from the FineGym and FineDiving datasets, enabling diverse and comprehensive evaluation. FineQuest achieves state-of-the-art performance on these benchmarks as well as the existing SPORTU dataset, while maintains strong general VideoQA capabilities.
Static analysis tools are widely used to detect bugs, vulnerabilities, and code smells. Traditionally, developers must resolve these warnings manually. Because this process is tedious, developers sometimes ignore warnings, leading to an accumulation of warnings and a degradation of code quality. This paper presents CodeCureAgent, an approach that harnesses LLM-based agents to automatically analyze, classify, and repair static analysis warnings. Unlike previous work, our method does not follow a predetermined algorithm. Instead, we adopt an agentic framework that iteratively invokes tools to gather additional information from the codebase (e.g., via code search) and edit the codebase to resolve the warning. CodeCureAgent detects and suppresses false positives, while fixing true positives when identified. We equip CodeCureAgent with a three-step heuristic to approve patches: (1) build the project, (2) verify that the warning disappears without introducing new warnings, and (3) run the test suite. We evaluate CodeCureAgent on a dataset of 1,000 SonarQube warnings found in 106 Java projects and covering 291 distinct rules. Our approach produces plausible fixes for 96.8% of the warnings, outperforming state-of-the-art baseline approaches by 30.7% and 29.2% in plausible-fix rate, respectively. Manual inspection of 291 cases reveals a correct-fix rate of 86.3%, showing that CodeCureAgent can reliably repair static analysis warnings. The approach incurs LLM costs of about 2.9 cents (USD) and an end-to-end processing time of about four minutes per warning. We envision CodeCureAgent helping to clean existing codebases and being integrated into CI/CD pipelines to prevent the accumulation of static analysis warnings.
Declaration of Performance (DoP) documents, mandated by EU regulation, certify the performance of construction products. While some of their content is standardized, DoPs vary widely in layout, language, schema, and format, posing challenges for automated key-value pair extraction (KVP) and question answering (QA). Existing static or LLM-only IE pipelines often hallucinate and fail to adapt to this structural diversity. Our domain-specific, stateful agentic system addresses these challenges through a planner-executor-responder architecture. The system infers user intent, detects document modality, and orchestrates tools dynamically for robust, traceable reasoning while avoiding tool misuse or execution loops. Evaluation on a curated DoP dataset demonstrates improved robustness across formats and languages, offering a scalable solution for structured data extraction in regulated workflows.
Zero-knowledge proofs (ZKPs) are increasingly deployed in domains such as privacy-preserving authentication, blockchain scalability, and secure finance. However, authoring ZK programs remains challenging: unlike mainstream programming, ZK development requires reasoning about finite field arithmetic, constraint systems, and gadgets, making it knowledge-intensive and error-prone. While large language models (LLMs) have demonstrated strong code generation capabilities in general-purpose languages, their effectiveness for ZK programming, where correctness hinges on both language mastery and gadget-level reasoning, remains unexplored. To address this gap, we propose \textsc{ZK-Eval}, a domain-specific evaluation pipeline that probes LLM capabilities at three levels: language knowledge, gadget competence, and end-to-end program generation. Our evaluation of four state-of-the-art LLMs reveals that models excel at surface-level syntax but struggle with gadget usage and semantic correctness, often yielding incorrect programs. Based on these insights, we introduce \textsc{ZK-Coder}, an agentic framework that augments LLMs with constraint sketching, guided retrieval, and interactive repair. Experiments on Circom and Noir show substantial gains, with success rates improving from 17.35\% to 83.38\% and from 32.21\% to 90.05\%, respectively. With \textsc{ZK-Eval} and \textsc{ZK-Coder}, we establish a foundation for systematically measuring and augmenting LLMs in ZK code generation to lower barriers for practitioners and advance trustworthy computation.
Recent advancements in Large Language Models (LLMs) has lead to the development of agents capable of complex reasoning and interaction with external tools. In enterprise contexts, the effective use of such tools that are often enabled by application programming interfaces (APIs), is hindered by poor documentation, complex input or output schema, and large number of operations. These challenges make tool selection difficult and reduce the accuracy of payload formation by up to 25%. We propose ACE, an automated tool creation and enrichment framework that transforms enterprise APIs into LLM-compatible tools. ACE, (i) generates enriched tool specifications with parameter descriptions and examples to improve selection and invocation accuracy, and (ii) incorporates a dynamic shortlisting mechanism that filters relevant tools at runtime, reducing prompt complexity while maintaining scalability. We validate our framework on both proprietary and open-source APIs and demonstrate its integration with agentic frameworks. To the best of our knowledge, ACE is the first end-to-end framework that automates the creation, enrichment, and dynamic selection of enterprise API tools for LLM agents.
Time series reasoning treats time as a first-class axis and incorporates intermediate evidence directly into the answer. This survey defines the problem and organizes the literature by reasoning topology with three families: direct reasoning in one step, linear chain reasoning with explicit intermediates, and branch-structured reasoning that explores, revises, and aggregates. The topology is crossed with the main objectives of the field, including traditional time series analysis, explanation and understanding, causal inference and decision making, and time series generation, while a compact tag set spans these axes and captures decomposition and verification, ensembling, tool use, knowledge access, multimodality, agent loops, and LLM alignment regimes. Methods and systems are reviewed across domains, showing what each topology enables and where it breaks down in faithfulness or robustness, along with curated datasets, benchmarks, and resources that support study and deployment (https://github.com/blacksnail789521/Time-Series-Reasoning-Survey). Evaluation practices that keep evidence visible and temporally aligned are highlighted, and guidance is distilled on matching topology to uncertainty, grounding with observable artifacts, planning for shift and streaming, and treating cost and latency as design budgets. We emphasize that reasoning structures must balance capacity for grounding and self-correction against computational cost and reproducibility, while future progress will likely depend on benchmarks that tie reasoning quality to utility and on closed-loop testbeds that trade off cost and risk under shift-aware, streaming, and long-horizon settings. Taken together, these directions mark a shift from narrow accuracy toward reliability at scale, enabling systems that not only analyze but also understand, explain, and act on dynamic worlds with traceable evidence and credible outcomes.
The application of language models to project-level vulnerability detection remains challenging, owing to the dual requirement of accurately localizing security-sensitive code and correctly correlating and reasoning over complex program context. We present VulAgent, a multi-agent vulnerability detection framework based on hypothesis validation. Our design is inspired by how human auditors review code: when noticing a sensitive operation, they form a hypothesis about a possible vulnerability, consider potential trigger paths, and then verify the hypothesis against the surrounding context. VulAgent implements a semantics-sensitive, multi-view detection pipeline: specialized agents, each aligned to a specific analysis perspective (e.g., memory, authorization), collaboratively surface and precisely localize sensitive code sites with higher coverage. Building on this, VulAgent adopts a hypothesis-validation paradigm: for each vulnerability report, it builds hypothesis conditions and a trigger path, steering the LLM to target the relevant program context and defensive checks during verification, which reduces false positives. On average across the two datasets, VulAgent improves overall accuracy by 6.6%, increases the correct identification rate of vulnerable--fixed code pairs by up to 450% (246% on average), and reduces the false positive rate by about 36% compared with state-of-the-art LLM-based baselines.
Decades' advances in digital health technologies, such as electronic health records, have largely streamlined routine clinical processes. Yet, most these systems are still hard to learn and use: Clinicians often face the burden of managing multiple tools, repeating manual actions for each patient, navigating complicated UI trees to locate functions, and spending significant time on administration instead of caring for patients. The recent rise of large language model (LLM) based agents demonstrates exceptional capability in coding and computer operation, revealing the potential for humans to interact with operating systems and software not by direct manipulation, but by instructing agents through natural language. This shift highlights the need for an abstraction layer, an agent-computer interface, that translates human language into machine-executable commands. In digital healthcare, however, requires a more domain-specific abstractions that strictly follow trusted clinical guidelines and procedural standards to ensure safety, transparency, and compliance. To address this need, we present \textbf{MedicalOS}, a unified agent-based operational system designed as such a domain-specific abstract layer for healthcare. It translates human instructions into pre-defined digital healthcare commands, such as patient inquiry, history retrieval, exam management, report generation, referrals, treatment planning, that we wrapped as off-the-shelf tools using machine languages (e.g., Python, APIs, MCP, Linux). We empirically validate MedicalOS on 214 patient cases across 22 specialties, demonstrating high diagnostic accuracy and confidence, clinically sound examination requests, and consistent generation of structured reports and medication recommendations. These results highlight MedicalOS as a trustworthy and scalable foundation for advancing workflow automation in clinical practice.
Early detection of Alzheimer's disease and related dementias (ADRD) is critical for timely intervention, yet most diagnoses are delayed until advanced stages. While comprehensive patient narratives are essential for accurate diagnosis, prior work has largely focused on screening studies that classify cognitive status from interactions rather than supporting the diagnostic process. We designed voice-interactive conversational agents, leveraging large language models (LLMs), to elicit narratives relevant to ADRD from patients and informants. We evaluated the agent with 30 adults with suspected ADRD through conversation analysis (n=30), user surveys (n=19), and clinical validation against blinded specialist interviews (n=24). Symptoms detected by the agent aligned well with those identified by specialists across symptoms. Users appreciated the agent's patience and systematic questioning, which supported engagement and expression of complex, hard-to-describe experiences. This preliminary work suggests conversational agents may serve as structured front-end tools for dementia assessment, highlighting interaction design considerations in sensitive healthcare contexts.
Software development has entered a new era where large language models (LLMs) now serve as general-purpose reasoning engines, enabling natural language interaction and transformative applications across diverse domains. This paradigm is now extending into computer-aided engineering (CAE). Recent applications of LLMs in CAE have successfully automated routine tasks, including CAD model generation and FEM simulations. Nevertheless, these contributions, which primarily serve to reduce manual labor, are often insufficient for addressing the significant computational challenges posed by large-scale, high-dimensional systems. To this aim, we first introduce the concept of LLM-empowered CAE agent, where LLMs act as autonomous collaborators that plan, execute, and adapt CAE workflows. Then, we propose an LLM-empowered CAE agent for data-free model order reduction (MOR), a powerful yet underused approach for ultra-fast large-scale parametric analysis due to the intrusive nature and labor-intensive redevelopment of solvers. LLMs can alleviate this barrier by automating derivations, code restructuring, and implementation, making intrusive MOR both practical and broadly accessible. To demonstrate feasibility, we present an LLM-empowered CAE agent for solving ultra-large-scale space-parameter-time (S-P-T) physical problems using Tensor-decomposition-based A Priori Surrogates (TAPS). Our results show that natural language prompts describing parametric partial differential equations (PDEs) can be translated into efficient solver implementations, substantially reducing human effort while producing high-fidelity reduced-order models. Moreover, LLMs can synthesize novel MOR solvers for unseen cases such as nonlinear and high-dimensional parametric problems based on their internal knowledge base. This highlights the potential of LLMs to establish the foundation for next-generation CAE systems.
The emergence of Large Language Models (LLMs) has significantly advanced solutions across various domains, from political science to software development. However, these models are constrained by their training data, which is static and limited to information available up to a specific date. Additionally, their generalized nature often necessitates fine-tuning -- whether for classification or instructional purposes -- to effectively perform specific downstream tasks. AI agents, leveraging LLMs as their core, mitigate some of these limitations by accessing external tools and real-time data, enabling applications such as live weather reporting and data analysis. In industrial settings, AI agents are transforming operations by enhancing decision-making, predictive maintenance, and process optimization. For example, in manufacturing, AI agents enable near-autonomous systems that boost productivity and support real-time decision-making. Despite these advancements, AI agents remain vulnerable to security threats, including prompt injection attacks, which pose significant risks to their integrity and reliability. To address these challenges, this paper proposes a framework for integrating Role-Based Access Control (RBAC) into AI agents, providing a robust security guardrail. This framework aims to support the effective and scalable deployment of AI agents, with a focus on on-premises implementations.
Prompt engineering is crucial for leveraging large language models (LLMs), but existing methods often rely on a single optimization trajectory, limiting adaptability and efficiency while suffering from narrow perspectives, gradient conflicts, and high computational cost. We propose MAPGD (Multi-Agent Prompt Gradient Descent), a framework integrating multi-agent collaboration with gradient-based optimization. MAPGD features specialized agents for task clarity, example selection, format design, and stylistic refinement; semantic gradient coordination to resolve conflicts; bandit-based candidate selection for efficient exploration-exploitation; and theoretical convergence guarantees. Experiments on classification, generation, and reasoning tasks show MAPGD outperforms single-agent and random baselines in accuracy and efficiency. Ablations confirm the benefits of gradient fusion, agent specialization, and conflict resolution, providing a unified, gradient-inspired multi-agent approach to robust and interpretable prompt optimization.
Large language models (LLMs) have demonstrated promise in emulating human-like responses across a wide range of tasks. In this paper, we propose a novel alignment framework that treats LLMs as agent proxies for human survey respondents, affording a cost-effective and steerable solution to two pressing challenges in the social sciences: the rising cost of survey deployment and the growing demographic imbalance in survey response data. Drawing inspiration from the theory of revealed preference, we formulate alignment as a two-stage problem: constructing diverse agent personas called endowments that simulate plausible respondent profiles, and selecting a representative subset to approximate a ground-truth population based on observed data. To implement the paradigm, we introduce P2P, a system that steers LLM agents toward representative behavioral patterns using structured prompt engineering, entropy-based sampling, and regression-based selection. Unlike personalization-heavy approaches, our alignment approach is demographic-agnostic and relies only on aggregate survey results, offering better generalizability and parsimony. Beyond improving data efficiency in social science research, our framework offers a testbed for studying the operationalization of pluralistic alignment. We demonstrate the efficacy of our approach on real-world opinion survey datasets, showing that our aligned agent populations can reproduce aggregate response patterns with high fidelity and exhibit substantial response diversity, even without demographic conditioning.
Developing effective prompts demands significant cognitive investment to generate reliable, high-quality responses from Large Language Models (LLMs). By deploying case-specific prompt engineering techniques that streamline frequently performed life sciences workflows, researchers could achieve substantial efficiency gains that far exceed the initial time investment required to master these techniques. The Prompt Report published in 2025 outlined 58 different text-based prompt engineering techniques, highlighting the numerous ways prompts could be constructed. To provide actionable guidelines and reduce the friction of navigating these various approaches, we distil this report to focus on 6 core techniques: zero-shot, few-shot approaches, thought generation, ensembling, self-criticism, and decomposition. We breakdown the significance of each approach and ground it in use cases relevant to life sciences, from literature summarization and data extraction to editorial tasks. We provide detailed recommendations for how prompts should and shouldn't be structured, addressing common pitfalls including multi-turn conversation degradation, hallucinations, and distinctions between reasoning and non-reasoning models. We examine context window limitations, agentic tools like Claude Code, while analyzing the effectiveness of Deep Research tools across OpenAI, Google, Anthropic and Perplexity platforms, discussing current limitations. We demonstrate how prompt engineering can augment rather than replace existing established individual practices around data processing and document editing. Our aim is to provide actionable guidance on core prompt engineering principles, and to facilitate the transition from opportunistic prompting to an effective, low-friction systematic practice that contributes to higher quality research.
GUI agents built on LVLMs are increasingly used to interact with websites. However, their exposure to open-world content makes them vulnerable to Environmental Injection Attacks (EIAs) that hijack agent behavior via webpage elements. Many recent studies assume the attacker to be a regular user who can only upload a single trigger image, which is more realistic than earlier assumptions of website-level administrative control. However, these works still fall short of realism: (1) the trigger's position and surrounding context remain largely fixed between training and testing, failing to capture the dynamic nature of real webpages and (2) the trigger often occupies an unrealistically large area, whereas real-world images are typically small. To better reflect real-world scenarios, we introduce a more realistic threat model where the attacker is a regular user and the trigger image is small and embedded within a dynamically changing environment. As a result, existing attacks prove largely ineffective under this threat model. To better expose the vulnerabilities of GUI agents, we propose Chameleon, an attack framework with two main novelties. The first is LLM-Driven Environment Simulation, which automatically generates diverse and high-fidelity webpage simulations. The second is Attention Black Hole, which transforms attention weights into explicit supervisory signals that guide the agent's focus toward the trigger region. We evaluate Chameleon on 6 realistic websites and 4 representative LVLM-powered GUI agents, where it significantly outperforms existing methods. Ablation studies confirm that both novelties are critical to performance. Our findings reveal underexplored vulnerabilities in modern GUI agents and establish a robust foundation for future research on defense in open-world GUI agent systems. The code is publicly available at https://github.com/zhangyitonggg/attack2gui.
While many text-to-audio systems produce monophonic or fixed-stereo outputs, generating audio with user-defined spatial properties remains a challenge. Existing deep learning-based spatialization methods often rely on latent-space manipulations, which can limit direct control over psychoacoustic parameters critical to spatial perception. To address this, we introduce STASE, a system that leverages a Large Language Model (LLM) as an agent to interpret spatial cues from text. A key feature of STASE is the decoupling of semantic interpretation from a separate, physics-based spatial rendering engine, which facilitates interpretable and user-controllable spatial reasoning. The LLM processes prompts through two main pathways: (i) Description Prompts, for direct mapping of explicit spatial information (e.g., "place the lead guitar at 45{\deg} azimuth, 10 m distance"), and (ii) Abstract Prompts, where a Retrieval-Augmented Generation (RAG) module retrieves relevant spatial templates to inform the rendering. This paper details the STASE workflow, discusses implementation considerations, and highlights current challenges in evaluating generative spatial audio.
Large Language Model (LLM)-based agentic systems have shown strong capabilities across various tasks. However, existing multi-agent frameworks often rely on static or task-level workflows, which either over-process simple queries or underperform on complex ones, while also neglecting the efficiency-performance trade-offs across heterogeneous LLMs. To address these limitations, we propose Difficulty-Aware Agentic Orchestration (DAAO), a dynamic framework that adapts workflow depth, operator selection, and LLM assignment based on the difficulty of each input query. DAAO comprises three interdependent modules: a variational autoencoder (VAE) for difficulty estimation, a modular operator allocator, and a cost- and performance-aware LLM router. By leveraging heterogeneous LLMs and dynamically tailoring workflows, DAAO enables fine-grained, query-specific reasoning strategies. DAAO outperforms prior multi-agent systems in both accuracy and inference efficiency across six benchmarks. We will release our code and implementation details upon publication.
Synthetic data generation using large language models (LLMs) has emerged as a promising solution across various domains, particularly in medical field, to mitigate data collection challenges. However, existing studies mainly utilize LLMs to rewrite and complete existing medical records, where the limitations in data privacy, accuracy, and diversity sill exist, and additionally lack the ability to interact like real patients. To address these issues, we propose a realistic patient generation framework, Patient-Zero, which requires no real medical records. Patient-Zero first introduces a medically-aligned multi-step generation architecture, which builds comprehensive patient records through hierarchical medical knowledge injection without real medical records. Then, to optimize the virtual patient's interaction abilities with humans, Patient-Zero designs a dynamic updating mechanism to improve the consistency and conversational performance. Our framework enables the generation of contextually diverse patient records while maintaining strict medical coherence, supported by adaptive dialogue strategies and real-time clinical plausibility verification. Experimental results demonstrate that our model achieves good performance in accuracy, diversity, and consistency. After training with our generated virtual patients, existing models show significant improvements on the MedQA dataset.
The landscape of Large Language Models (LLMs) shifts rapidly towards dynamic, multi-agent systems. This introduces a fundamental challenge in establishing computational trust, specifically how one agent can verify that another's output was genuinely produced by a claimed LLM, and not falsified or generated by a cheaper or inferior model. To address this challenge, this paper proposes a verification framework that achieves tractable asymmetric effort, where the cost to verify a computation is substantially lower than the cost to perform it. Our approach is built upon the principle of deterministic replicability, a property inherent to autoregressive models that strictly necessitates a computationally homogeneous environment where all agents operate on identical hardware and software stacks. Within this defined context, our framework enables multiple validators to probabilistically audit small, random segments of an LLM's output and it distributes the verification workload effectively. The simulations demonstrated that targeted verification can be over 12 times faster than full regeneration, with tunable parameters to adjust the detection probability. By establishing a tractable mechanism for auditable LLM systems, our work offers a foundational layer for responsible AI and serves as a cornerstone for future research into the more complex, heterogeneous multi-agent systems.
The rapid progress of large language models (LLMs) has opened new opportunities for education. While learners can interact with academic papers through LLM-powered dialogue, limitations still exist: absence of structured organization and high text reliance can impede systematic understanding and engagement with complex concepts. To address these challenges, we propose Auto-Slides, an LLM-driven system that converts research papers into pedagogically structured, multimodal slides (e.g., diagrams and tables). Drawing on cognitive science, it creates a presentation-oriented narrative and allows iterative refinement via an interactive editor, in order to match learners' knowledge level and goals. Auto-Slides further incorporates verification and knowledge retrieval mechanisms to ensure accuracy and contextual completeness. Through extensive user studies, Auto-Slides enhances learners' comprehension and engagement compared to conventional LLM-based reading. Our contributions lie in designing a multi-agent framework for transforming academic papers into pedagogically optimized slides and introducing interactive customization for personalized learning.
Multi-agent debate (MAD) is an emerging approach to improving the reasoning capabilities of large language models (LLMs). Existing MAD methods rely on multiple rounds of interaction among agents to reach consensus, and the final output is selected by majority voting in the last round. However, this consensus-based design faces several limitations. First, multiple rounds of communication increases token overhead and limits scalability. Second, due to the inherent conformity of LLMs, agents that initially produce correct responses may be influenced by incorrect ones during the debate process, causing error propagation. Third, majority voting introduces randomness and unfairness in the decision-making phase, and can degrade the reasoning performance. To address these issues, we propose \textsc{Free-MAD}, a novel MAD framework that eliminates the need for consensus among agents. \textsc{Free-MAD} introduces a novel score-based decision mechanism that evaluates the entire debate trajectory rather than relying on the last round only. This mechanism tracks how each agent's reasoning evolves, enabling more accurate and fair outcomes. In addition, \textsc{Free-MAD} reconstructs the debate phase by introducing anti-conformity, a mechanism that enables agents to mitigate excessive influence from the majority. Experiments on eight benchmark datasets demonstrate that \textsc{Free-MAD} significantly improves reasoning performance while requiring only a single-round debate and thus reducing token costs. We also show that compared to existing MAD approaches, \textsc{Free-MAD} exhibits improved robustness in real-world attack scenarios.
The concept of the 'agent' has profoundly shaped Artificial Intelligence (AI) research, guiding development from foundational theories to contemporary applications like Large Language Model (LLM)-based systems. This paper critically re-evaluates the necessity and optimality of this agent-centric paradigm. We argue that its persistent conceptual ambiguities and inherent anthropocentric biases may represent a limiting framework. We distinguish between agentic systems (AI inspired by agency, often semi-autonomous, e.g., LLM-based agents), agential systems (fully autonomous, self-producing systems, currently only biological), and non-agentic systems (tools without the impression of agency). Our analysis, based on a systematic review of relevant literature, deconstructs the agent paradigm across various AI frameworks, highlighting challenges in defining and measuring properties like autonomy and goal-directedness. We argue that the 'agentic' framing of many AI systems, while heuristically useful, can be misleading and may obscure the underlying computational mechanisms, particularly in Large Language Models (LLMs). As an alternative, we propose a shift in focus towards frameworks grounded in system-level dynamics, world modeling, and material intelligence. We conclude that investigating non-agentic and systemic frameworks, inspired by complex systems, biology, and unconventional computing, is essential for advancing towards robust, scalable, and potentially non-anthropomorphic forms of general intelligence. This requires not only new architectures but also a fundamental reconsideration of our understanding of intelligence itself, moving beyond the agent metaphor.
Domain-specific embedding models have shown promise for applications that require specialized semantic understanding, such as coding agents and financial retrieval systems, often achieving higher performance gains than general models. However, state-of-the-art embedding models are typically based on LLMs, which contain billions of parameters, making deployment challenging in resource-constrained environments. Model compression through pruning offers a promising solution, but existing pruning methods treat all parameters uniformly, failing to distinguish between general semantic representations and domain-specific patterns, leading to suboptimal pruning decisions. Thus, we propose GAPrune, a pruning framework that addresses this challenge by considering both domain importance and preserving general linguistic foundation. Our method uses Fisher Information to measure importance and general-domain gradient alignment to assess parameter behavior, then combines these signals using our Domain Alignment Importance (DAI) scoring. Lower DAI scores indicate that the parameter is either less important for the domain task or creates conflicts between domain and general objectives. Experiments on two domain benchmarks, FinMTEB and ChemTEB, show that GAPrune maintains performance within 2.5% of dense models in one-shot pruning at 50% sparsity, while outperforming all baselines. With retraining in 100 steps, GAPrune achieves +4.51% improvement on FinMTEB and +1.73% on ChemTEB, demonstrating that our pruning strategy not only preserves but enhances domain-specific capabilities. Our findings demonstrate that principled pruning strategies can achieve model compression and enhanced domain specialization, providing the research community with a new approach for development.