Large language models (LLMs) are excellent at maintaining high-level, convincing dialogues. They are being fast deployed as chatbots and evaluators in sensitive areas, such as peer review and mental health applications. This, along with the disparate accounts on their reasoning capabilities, calls for a closer examination of LLMs and their comprehension of dialogue. In this work we begin by evaluating LLMs' ability to maintain a debate--one of the purest yet most complex forms of human communication. Then we measure how this capability relates to their understanding of what is being talked about, namely, their comprehension of dialogical structures and the pragmatic context. We find that LLMs are capable of maintaining coherent, persuasive debates, often swaying the beliefs of participants and audiences alike. We also note that awareness or suspicion of AI involvement encourage people to be more critical of the arguments made. When polling LLMs on their comprehension of deeper structures of dialogue, however, they cannot demonstrate said understanding. Our findings tie the shortcomings of LLMs-as-evaluators to their (in)ability to understand the context. More broadly, for the field of argumentation theory we posit that, if an agent can convincingly maintain a dialogue, it is not necessary for it to know what it is talking about. Hence, the modelling of pragmatic context and coherence are secondary to effectiveness.
Natural language generation (NLG) is increasingly deployed in high-stakes domains, yet common intrinsic evaluation methods, such as n-gram overlap or sentence plausibility, weakly correlate with actual decision-making efficacy. We propose a decision-oriented framework for evaluating generated text by directly measuring its influence on human and large language model (LLM) decision outcomes. Using market digest texts--including objective morning summaries and subjective closing-bell analyses--as test cases, we assess decision quality based on the financial performance of trades executed by human investors and autonomous LLM agents informed exclusively by these texts. Our findings reveal that neither humans nor LLM agents consistently surpass random performance when relying solely on summaries. However, richer analytical commentaries enable collaborative human-LLM teams to outperform individual human or agent baselines significantly. Our approach underscores the importance of evaluating generated text by its ability to facilitate synergistic decision-making between humans and LLMs, highlighting critical limitations of traditional intrinsic metrics.
Domain specific chatbot applications often involve multi step interactions, such as refining search filters, selecting multiple items, or performing comparisons. Traditional graphical user interfaces (GUIs) handle these workflows by providing explicit "Submit" (commit data) and "Reset" (discard data) actions, allowing back-end systems to track user intent unambiguously. In contrast, conversational agents rely on subtle language cues, which can lead to confusion and incomplete context management. This paper proposes modeling these GUI inspired metaphors acknowledgment (submit like) and context switching (reset-like) as explicit tasks within large language model (LLM) prompts. By capturing user acknowledgment, reset actions, and chain of thought (CoT) reasoning as structured session data, we preserve clarity, reduce user confusion, and align domain-specific chatbot interactions with back-end logic. We demonstrate our approach in hotel booking and customer management scenarios, highlighting improvements in multi-turn task coherence, user satisfaction, and efficiency.
Patents contain rich technical knowledge that can inspire innovative product ideas, yet accessing and interpreting this information remains a challenge. This work explores the use of Large Language Models (LLMs) and autonomous agents to mine and generate product concepts from a given patent. In this work, we design Agent Ideate, a framework for automatically generating product-based business ideas from patents. We experimented with open-source LLMs and agent-based architectures across three domains: Computer Science, Natural Language Processing, and Material Chemistry. Evaluation results show that the agentic approach consistently outperformed standalone LLMs in terms of idea quality, relevance, and novelty. These findings suggest that combining LLMs with agentic workflows can significantly enhance the innovation pipeline by unlocking the untapped potential of business idea generation from patent data.
In this paper, we propose to incorporate the blackboard architecture into LLM multi-agent systems (MASs) so that (1) agents with various roles can share all the information and others' messages during the whole problem-solving process, (2) agents that will take actions are selected based on the current content of the blackboard, and (3) the selection and execution round is repeated until a consensus is reached on the blackboard. We develop the first implementation of this proposal and conduct experiments on commonsense knowledge, reasoning and mathematical datasets. The results show that our system can be competitive with the SOTA static and dynamic MASs by achieving the best average performance, and at the same time manage to spend less tokens. Our proposal has the potential to enable complex and dynamic problem-solving where well-defined structures or workflows are unavailable.
Traditional Data+AI systems utilize data-driven techniques to optimize performance, but they rely heavily on human experts to orchestrate system pipelines, enabling them to adapt to changes in data, queries, tasks, and environments. For instance, while there are numerous data science tools available, developing a pipeline planning system to coordinate these tools remains challenging. This difficulty arises because existing Data+AI systems have limited capabilities in semantic understanding, reasoning, and planning. Fortunately, we have witnessed the success of large language models (LLMs) in enhancing semantic understanding, reasoning, and planning abilities. It is crucial to incorporate LLM techniques to revolutionize data systems for orchestrating Data+AI applications effectively. To achieve this, we propose the concept of a 'Data Agent' - a comprehensive architecture designed to orchestrate Data+AI ecosystems, which focuses on tackling data-related tasks by integrating knowledge comprehension, reasoning, and planning capabilities. We delve into the challenges involved in designing data agents, such as understanding data/queries/environments/tools, orchestrating pipelines/workflows, optimizing and executing pipelines, and fostering pipeline self-reflection. Furthermore, we present examples of data agent systems, including a data science agent, data analytics agents (such as unstructured data analytics agent, semantic structured data analytics agent, data lake analytics agent, and multi-modal data analytics agent), and a database administrator (DBA) agent. We also outline several open challenges associated with designing data agent systems.
Task-oriented dialogue (ToD) systems are designed to help users achieve specific goals through natural language interaction. While recent advances in large language models (LLMs) have significantly improved linguistic fluency and contextual understanding, building effective and emotionally intelligent ToD systems remains a complex challenge. Effective ToD systems must optimise for task success, emotional understanding and responsiveness, and precise information conveyance, all within inherently noisy and ambiguous conversational environments. In this work, we investigate architectural, representational, optimisational as well as emotional considerations of ToD systems. We set up systems covering these design considerations with a challenging evaluation environment composed of a natural-language user simulator coupled with an imperfect natural language understanding module. We propose \textbf{LUSTER}, an \textbf{L}LM-based \textbf{U}nified \textbf{S}ystem for \textbf{T}ask-oriented dialogue with \textbf{E}nd-to-end \textbf{R}einforcement learning with both short-term (user sentiment) and long-term (task success) rewards. Our findings demonstrate that combining LLM capability with structured reward modelling leads to more resilient and emotionally responsive ToD systems, offering a practical path forward for next-generation conversational agents.
Large Language Models (LLMs) have emerged as one of the most significant technological advancements in artificial intelligence in recent years. Their ability to understand, generate, and reason with natural language has transformed how we interact with AI systems. With the development of LLM-based agents and reinforcement-learning-based reasoning models, the study of applying reinforcement learning in agent frameworks has become a new research focus. However, all previous studies face the challenge of deciding the tool calling process and the reasoning process simultaneously, and the chain of reasoning was solely relied on the unprocessed raw result with redundant information and symbols unrelated to the task from the tool, which impose a heavy burden on the model's capability to reason. Therefore, in our research, we proposed a hierarchical framework Agent-as-tool that detach the tool calling process and the reasoning process, which enables the model to focus on the verbally reasoning process while the tool calling process is handled by another agent. Our work had achieved comparable results with only a slight reinforcement fine-tuning on 180 samples, and had achieved exceptionally well performance in Bamboogle with 63.2% of exact match and 75.2% in cover exact match, exceeding Search-R1 by 4.8% in exact match and 3.2% in cover exact match.
Large language models (LLMs) and vision-language models (VLMs) have the potential to transform biological research by enabling autonomous experimentation. Yet, their application remains constrained by rigid protocol design, limited adaptability to dynamic lab conditions, inadequate error handling, and high operational complexity. Here we introduce BioMARS (Biological Multi-Agent Robotic System), an intelligent platform that integrates LLMs, VLMs, and modular robotics to autonomously design, plan, and execute biological experiments. BioMARS uses a hierarchical architecture: the Biologist Agent synthesizes protocols via retrieval-augmented generation; the Technician Agent translates them into executable robotic pseudo-code; and the Inspector Agent ensures procedural integrity through multimodal perception and anomaly detection. The system autonomously conducts cell passaging and culture tasks, matching or exceeding manual performance in viability, consistency, and morphological integrity. It also supports context-aware optimization, outperforming conventional strategies in differentiating retinal pigment epithelial cells. A web interface enables real-time human-AI collaboration, while a modular backend allows scalable integration with laboratory hardware. These results highlight the feasibility of generalizable, AI-driven laboratory automation and the transformative role of language-based reasoning in biological research.
Improving customer service quality and response time are critical factors for maintaining customer loyalty and increasing a company's market share. While adopting emerging technologies such as Large Language Models (LLMs) is becoming a necessity to achieve these goals, the risk of hallucination remains a major challenge. In this paper, we present a multi-agent system to handle customer requests sent via SMS. This system integrates LLM based agents with fuzzy logic to mitigate hallucination risks.
Large language models (LLMs) have demonstrated impressive capabilities as autonomous agents with rapidly expanding applications in various domains. As these agents increasingly engage in socioeconomic interactions, identifying their potential for undesirable behavior becomes essential. In this work, we examine scenarios where they can choose to collude, defined as secretive cooperation that harms another party. To systematically study this, we investigate the behavior of LLM agents acting as sellers in simulated continuous double auction markets. Through a series of controlled experiments, we analyze how parameters such as the ability to communicate, choice of model, and presence of environmental pressures affect the stability and emergence of seller collusion. We find that direct seller communication increases collusive tendencies, the propensity to collude varies across models, and environmental pressures, such as oversight and urgency from authority figures, influence collusive behavior. Our findings highlight important economic and ethical considerations for the deployment of LLM-based market agents.
Intelligent control of Unmanned Aerial Vehicles (UAVs) swarms has emerged as a critical research focus, and it typically requires the swarm to navigate effectively while avoiding obstacles and achieving continuous coverage over multiple mission targets. Although traditional Multi-Agent Reinforcement Learning (MARL) approaches offer dynamic adaptability, they are hindered by the semantic gap in numerical communication and the rigidity of homogeneous role structures, resulting in poor generalization and limited task scalability. Recent advances in Large Language Model (LLM)-based control frameworks demonstrate strong semantic reasoning capabilities by leveraging extensive prior knowledge. However, due to the lack of online learning and over-reliance on static priors, these works often struggle with effective exploration, leading to reduced individual potential and overall system performance. To address these limitations, we propose a Role-Adaptive LLM-Driven Yoked navigation algorithm RALLY. Specifically, we first develop an LLM-driven semantic decision framework that uses structured natural language for efficient semantic communication and collaborative reasoning. Afterward, we introduce a dynamic role-heterogeneity mechanism for adaptive role switching and personalized decision-making. Furthermore, we propose a Role-value Mixing Network (RMIX)-based assignment strategy that integrates LLM offline priors with MARL online policies to enable semi-offline training of role selection strategies. Experiments in the Multi-Agent Particle Environment (MPE) environment and a Software-In-The-Loop (SITL) platform demonstrate that RALLY outperforms conventional approaches in terms of task coverage, convergence speed, and generalization, highlighting its strong potential for collaborative navigation in agentic multi-UAV systems.
AI agents are autonomous systems designed to perceive, reason, and act within dynamic environments. With the rapid advancements in generative AI (GenAI), large language models (LLMs) and multimodal large language models (MLLMs) have significantly improved AI agents' capabilities in semantic comprehension, complex reasoning, and autonomous decision-making. At the same time, the rise of Agentic AI highlights adaptability and goal-directed autonomy in dynamic and complex environments. LLMs-based AI Agents (LLM-Agents), MLLMs-based AI Agents (MLLM-Agents), and Agentic AI contribute to expanding AI's capabilities in information processing, environmental perception, and autonomous decision-making, opening new avenues for smart manufacturing. However, the definitions, capability boundaries, and practical applications of these emerging AI paradigms in smart manufacturing remain unclear. To address this gap, this study systematically reviews the evolution of AI and AI agent technologies, examines the core concepts and technological advancements of LLM-Agents, MLLM-Agents, and Agentic AI, and explores their potential applications in and integration into manufacturing, along with the potential challenges they may face.
Copy-paste-modify is a widespread and pragmatic practice in software development, where developers adapt reused code snippets, sourced from platforms such as Stack Overflow, GitHub, or LLM outputs, into their local codebase. A critical yet underexplored aspect of this adaptation is code wiring, which involves substituting unresolved variables in the pasted code with suitable ones from the surrounding context. Existing solutions either rely on heuristic rules or historical templates, often failing to effectively utilize contextual information, despite studies showing that over half of adaptation cases are context-dependent. In this paper, we introduce WIRL, an LLM-based agent for code wiring framed as a Retrieval-Augmented Generation (RAG) infilling task. WIRL combines an LLM, a customized toolkit, and an orchestration module to identify unresolved variables, retrieve context, and perform context-aware substitutions. To balance efficiency and autonomy, the agent adopts a mixed strategy: deterministic rule-based steps for common patterns, and a state-machine-guided decision process for intelligent exploration. We evaluate WIRL on a carefully curated, high-quality dataset consisting of real-world code adaptation scenarios. Our approach achieves an exact match precision of 91.7% and a recall of 90.0%, outperforming advanced LLMs by 22.6 and 13.7 percentage points in precision and recall, respectively, and surpassing IntelliJ IDEA by 54.3 and 49.9 percentage points. These results underscore its practical utility, particularly in contexts with complex variable dependencies or multiple unresolved variables. We believe WIRL paves the way for more intelligent and context-aware developer assistance in modern IDEs.
In this paper we discuss the capability of large language models to base their answer and provide proper references when dealing with legal matters of non-english and non-chinese speaking country. We discuss the history of legal information retrieval, the difference between case law and statute law, its impact on the legal tasks and analyze the latest research in this field. Basing on that background we introduce gAIus, the architecture of the cognitive LLM-based agent, whose responses are based on the knowledge retrieved from certain legal act, which is Polish Civil Code. We propose a retrieval mechanism which is more explainable, human-friendly and achieves better results than embedding-based approaches. To evaluate our method we create special dataset based on single-choice questions from entrance exams for law apprenticeships conducted in Poland. The proposed architecture critically leveraged the abilities of used large language models, improving the gpt-3.5-turbo-0125 by 419%, allowing it to beat gpt-4o and lifting gpt-4o-mini score from 31% to 86%. At the end of our paper we show the possible future path of research and potential applications of our findings.
As autonomous agents powered by large language models (LLMs) continue to demonstrate potential across various assistive tasks, ensuring their safe and reliable behavior is crucial for preventing unintended consequences. In this work, we introduce CIP, a novel technique that leverages causal influence diagrams (CIDs) to identify and mitigate risks arising from agent decision-making. CIDs provide a structured representation of cause-and-effect relationships, enabling agents to anticipate harmful outcomes and make safer decisions. Our approach consists of three key steps: (1) initializing a CID based on task specifications to outline the decision-making process, (2) guiding agent interactions with the environment using the CID, and (3) iteratively refining the CID based on observed behaviors and outcomes. Experimental results demonstrate that our method effectively enhances safety in both code execution and mobile device control tasks.
Recent progress in large language models (LLMs) has enabled the development of autonomous web agents capable of navigating and interacting with real websites. However, evaluating such agents remains challenging due to the instability and inconsistency of existing benchmarks, which often rely on dynamic content or oversimplified simulations. In this work, we introduce WebArXiv, a static and time-invariant benchmark comprising 275 web-based tasks grounded in the arXiv platform. WebArXiv ensures reproducible and reliable evaluation by anchoring tasks in fixed web snapshots with deterministic ground truths and standardized action trajectories. Through behavioral analysis, we identify a common failure mode, Rigid History Reflection, where agents over-rely on fixed interaction histories. To address this, we propose a lightweight dynamic reflection mechanism that allows agents to selectively retrieve relevant past steps during decision-making. We evaluate ten state-of-the-art web agents on WebArXiv. Results demonstrate clear performance differences across agents and validate the effectiveness of our proposed reflection strategy.
The long-standing vision of intelligent cities is to create efficient, livable, and sustainable urban environments using big data and artificial intelligence technologies. Recently, the advent of Large Language Models (LLMs) has opened new ways toward realizing this vision. With powerful semantic understanding and reasoning capabilities, LLMs can be deployed as intelligent agents capable of autonomously solving complex problems across domains. In this article, we focus on Urban LLM Agents, which are LLM-powered agents that are semi-embodied within the hybrid cyber-physical-social space of cities and used for system-level urban decision-making. First, we introduce the concept of urban LLM agents, discussing their unique capabilities and features. Second, we survey the current research landscape from the perspective of agent workflows, encompassing urban sensing, memory management, reasoning, execution, and learning. Third, we categorize the application domains of urban LLM agents into five groups: urban planning, transportation, environment, public safety, and urban society, presenting representative works in each group. Finally, we discuss trustworthiness and evaluation issues that are critical for real-world deployment, and identify several open problems for future research. This survey aims to establish a foundation for the emerging field of urban LLM agents and to provide a roadmap for advancing the intersection of LLMs and urban intelligence. A curated list of relevant papers and open-source resources is maintained and continuously updated at https://github.com/usail-hkust/Awesome-Urban-LLM-Agents.
Multi-agent systems empowered by large language models (LLMs) have demonstrated remarkable capabilities in a wide range of downstream applications, including machine translation. However, the potential of LLMs in translating Hong Kong legal judgments remains uncertain due to challenges such as intricate legal terminology, culturally embedded nuances, and strict linguistic structures. In this work, we introduce TransLaw, a novel multi-agent framework implemented for real-world Hong Kong case law translation. It employs three specialized agents, namely, Translator, Annotator, and Proofreader, to collaboratively produce translations for high accuracy in legal meaning, appropriateness in style, and adequate coherence and cohesion in structure. This framework supports customizable LLM configurations and achieves tremendous cost reduction compared to professional human translation services. We evaluated its performance using 13 open-source and commercial LLMs as agents and obtained interesting findings, including that it surpasses GPT-4o in legal semantic accuracy, structural coherence, and stylistic fidelity, yet trails human experts in contextualizing complex terminology and stylistic naturalness. Our platform website is available at CityUHK, and our bilingual judgment corpus used for the evaluation is available at Hugging Face.
Moral judgment is integral to large language model (LLM) alignment and social reasoning. As multi-agent systems gain prominence, it becomes crucial to understand how LLMs function collectively during collaboration, compared to individual agents. In human moral judgment, group deliberation leads to a utilitarian boost: a tendency to endorse norm violations that maximize benefits for the greatest number of people despite harms. We study whether a similar dynamic emerges in multi-agent LLM systems. We tested six models on well-established sets of moral dilemmas across two conditions: (1) Solo, where models reasoned independently, and (2) Group, where they engaged in multi-turn discussions in pairs or triads. In personal moral dilemmas, where agents must decide to directly harm one individual to maximize the utility for others, all models found moral violations to be more acceptable when part of a group than individually, similar to human experiments. Some models endorsed actions that maximized overall well-being, even if they benefited strangers over familiar individuals. Others became more willing to violate moral norms in groups. However, while human groups show a similar action bias, the mechanism for their utilitarian boost differs from LLMs. Whereas the human shift comes from heightened sensitivity to decision outcomes, LLM groups show either reduced norm sensitivity or enhanced impartiality. This suggests that while the surface behavior of LLM collectives mimics human group reasoning, the underlying drivers differ. We discuss the implications for AI alignment, multi-agent design, and artificial moral reasoning.
We investigate how Large Language Models (LLMs) behave when simulating political discourse on social media. Leveraging 21 million interactions on X during the 2024 U.S. presidential election, we construct LLM agents based on 1,186 real users, prompting them to reply to politically salient tweets under controlled conditions. Agents are initialized either with minimal ideological cues (Zero Shot) or recent tweet history (Few Shot), allowing one-to-one comparisons with human replies. We evaluate three model families (Gemini, Mistral, and DeepSeek) across linguistic style, ideological consistency, and toxicity. We find that richer contextualization improves internal consistency but also amplifies polarization, stylized signals, and harmful language. We observe an emergent distortion that we call "generation exaggeration": a systematic amplification of salient traits beyond empirical baselines. Our analysis shows that LLMs do not emulate users, they reconstruct them. Their outputs, indeed, reflect internal optimization dynamics more than observed behavior, introducing structural biases that compromise their reliability as social proxies. This challenges their use in content moderation, deliberative simulations, and policy modeling.
The increasing complexity of computational demands has accelerated the adoption of domain-specific accelerators, yet traditional hardware design methodologies remain constrained by prolonged development and verification cycles. High-Level Synthesis (HLS) bridges the gap between software and hardware by enabling hardware design from high-level programming languages. However, its widespread adoption is hindered by strict coding constraints and intricate hardware-specific optimizations, creating significant obstacles for developers. Recent advancements in Large Language Models (LLMs) demonstrate substantial potential in hardware design automation. However, their effectiveness is limited by the scarcity of high-quality datasets, particularly in the context of HLS. To address these challenges, we introduce ChatHLS, an agile HLS design automation and optimization workflow that leverages fine-tuned LLMs integrated within a multi-agent framework for error correction and design optimization. Our extensive evaluations reveal that ChatHLS achieves an average repair pass rate of 82.7% over 612 test cases, outperforming the GPT-4o and Llama3-8B by 19.1% and 63.0%, respectively. Furthermore, ChatHLS delivers performance enhancements ranging from 1.9$\times$ to 14.8$\times$ upon resource-constrained kernels. By enabling sophisticated optimization reasoning within practical computational budgets, ChatHLS attains a 4.9$\times$ geometric mean speedup compared to state-of-the-art DSL-based approaches. These results underscore the potential of ChatHLS in substantially expediting hardware development cycles while maintaining rigorous standards of design reliability and optimization quality.
Math reasoning has become the poster child of progress in large language models (LLMs), with new models rapidly surpassing human-level performance on benchmarks like MATH and AIME. But as math leaderboards improve week by week, it is worth asking: do these gains reflect broader problem-solving ability or just narrow overfitting? To answer this question, we evaluate over 20 open-weight reasoning-tuned models across a broad suite of tasks, including math, scientific QA, agent planning, coding, and standard instruction-following. We surprisingly find that most models that succeed in math fail to transfer their gains to other domains. To rigorously study this phenomenon, we conduct controlled experiments on Qwen3-14B models using math-only data but different tuning methods. We find that reinforcement learning (RL)-tuned models generalize well across domains, while supervised fine-tuning (SFT)-tuned models often forget general capabilities. Latent-space representation and token-space distribution shift analyses reveal that SFT induces substantial representation and output drift, while RL preserves general-domain structure. Our results suggest a need to rethink standard post-training recipes, particularly the reliance on SFT-distilled data for advancing reasoning models.
Conformance testing is essential for ensuring that protocol implementations comply with their specifications. However, traditional testing approaches involve manually creating numerous test cases and scripts, making the process labor-intensive and inefficient. Recently, Large Language Models (LLMs) have demonstrated impressive text comprehension and code generation abilities, providing promising opportunities for automation. In this paper, we propose iPanda, the first end-to-end framework that leverages LLMs to automate protocol conformance testing. Given a protocol specification document and its implementation, iPanda first employs a keyword-based method to automatically generate comprehensive test cases. Then, it utilizes a code-based retrieval-augmented generation approach to effectively interpret the implementation and produce executable test code. To further enhance code quality, iPanda incorporates an iterative self-correction mechanism to refine generated test scripts interactively. Finally, by executing and analyzing the generated tests, iPanda systematically verifies compliance between implementations and protocol specifications. Comprehensive experiments on various protocols show that iPanda significantly outperforms pure LLM-based approaches, improving the success rate (Pass@1) of test-code generation by factors ranging from 4.675 times to 10.751 times.
Recent advances in reinforcement learning have shown that language models can develop sophisticated reasoning through training on tasks with verifiable rewards, but these approaches depend on human-curated problem-answer pairs and domain-specific reward engineering. We introduce SPIRAL, a self-play framework where models learn by playing multi-turn, zero-sum games against continuously improving versions of themselves, eliminating the need for human supervision. Through self-play, SPIRAL generates an infinite curriculum of progressively challenging problems as models must constantly adapt to stronger opponents. To enable this self-play training at scale, We implement a fully online, multi-turn, multi-agent reinforcement learning system for LLMs and propose role-conditioned advantage estimation (RAE) to stabilize multi-agent training. Using SPIRAL, self-play on zero-sum games produces reasoning capabilities that transfer broadly. Training Qwen3-4B-Base on Kuhn Poker alone achieves 8.6% improvement on math and 8.4% on general reasoning, outperforming SFT on 25,000 expert game trajectories. Analysis reveals that this transfer occurs through three cognitive patterns: systematic decomposition, expected value calculation, and case-by-case analysis. Multi-game training (TicTacToe, Kuhn Poker, Simple Negotiation) further enhances performance as each game develops distinct reasoning strengths. Applying SPIRAL to a strong reasoning model (DeepSeek-R1-Distill-Qwen-7B) can still lead to 2.0% average improvement. These results demonstrate that zero-sum games naturally develop transferable reasoning capabilities, highlighting a promising direction for autonomous reasoning development.
The proliferation of agentic Large Language Models (LLMs) on personal devices introduces a new class of workloads characterized by a dichotomy of objectives. Reactive tasks, initiated by users, demand immediate, low-latency responses, while proactive tasks operate invisibly and prioritize throughput. Existing on-device LLM engines, designed for isolated inferences, fail to efficiently manage these concurrent and conflicting requests on consumer-grade heterogeneous SoCs with CPU, integrated GPU, and NPU. This paper introduces Agent.xpu, an efficient serving system for agentic LLM workloads on memory-unified heterogeneous SoCs. With dedicated offline profiling, Agent.xpu first constructs a heterogeneous execution graph, which fuses and chunks model kernels for affinity-guided, elastic accelerator mapping with predictive kernel annotation. At runtime, its online scheduler enables fine-grained, kernel-level preemption to guarantee the responsiveness of reactive tasks. To maximize SoC utilization, it adopts slack-aware kernel backfill to opportunistically append proactive tasks, and mitigates NPU-iGPU contention via bandwidth-aware dispatch. Evaluation on an Intel Core Ultra SoC shows that Agent.xpu achieves 4.6$\times$ lower latency for reactive tasks and sustains 1.6$\times$-6.8$\times$ higher throughput for proactive tasks compared to state-of-the-art inference engines.
Congenital heart disease (CHD) presents complex, lifelong challenges often underrepresented in traditional clinical metrics. While unstructured narratives offer rich insights into patient and caregiver experiences, manual thematic analysis (TA) remains labor-intensive and unscalable. We propose a fully automated large language model (LLM) pipeline that performs end-to-end TA on clinical narratives, which eliminates the need for manual coding or full transcript review. Our system employs a novel multi-agent framework, where specialized LLM agents assume roles to enhance theme quality and alignment with human analysis. To further improve thematic relevance, we optionally integrate reinforcement learning from human feedback (RLHF). This supports scalable, patient-centered analysis of large qualitative datasets and allows LLMs to be fine-tuned for specific clinical contexts.
While the Internet's core infrastructure was designed to be open and universal, today's application layer is dominated by closed, proprietary platforms. Open and interoperable APIs require significant investment, and market leaders have little incentive to enable data exchange that could erode their user lock-in. We argue that LLM-based agents fundamentally disrupt this status quo. Agents can automatically translate between data formats and interact with interfaces designed for humans: this makes interoperability dramatically cheaper and effectively unavoidable. We name this shift universal interoperability: the ability for any two digital services to exchange data seamlessly using AI-mediated adapters. Universal interoperability undermines monopolistic behaviours and promotes data portability. However, it can also lead to new security risks and technical debt. Our position is that the ML community should embrace this development while building the appropriate frameworks to mitigate the downsides. By acting now, we can harness AI to restore user freedom and competitive markets without sacrificing security.
Large language models (LLMs) have exhibited expert-level capabilities across various domains. However, their abilities to solve problems in Operations Research (OR) -- the analysis and optimization of mathematical models derived from real-world problems or their verbal descriptions -- remain underexplored. In this work, we take a first step toward evaluating LLMs' abilities to solve stochastic modeling problems, a core class of OR problems characterized by uncertainty and typically involving tools from probability, statistics, and stochastic processes. We manually procure a representative set of graduate-level homework and doctoral qualification-exam problems and test LLMs' abilities to solve them. We further leverage SimOpt, an open-source library of simulation-optimization problems and solvers, to investigate LLMs' abilities to make real-world decisions under uncertainty. Our results show that, though a nontrivial amount of work is still needed to reliably automate the stochastic modeling pipeline in reality, state-of-the-art LLMs demonstrate proficiency on par with human experts in both classroom and practical settings. These findings highlight the potential of building AI agents that assist OR researchers and amplify the real-world impact of OR through automation.
Recent advances in large language models (LLMs) have catalyzed the rise of autonomous AI agents capable of perceiving, reasoning, and acting in dynamic, open-ended environments. These large-model agents mark a paradigm shift from static inference systems to interactive, memory-augmented entities. While these capabilities significantly expand the functional scope of AI, they also introduce qualitatively novel security risks - such as memory poisoning, tool misuse, reward hacking, and emergent misalignment - that extend beyond the threat models of conventional systems or standalone LLMs. In this survey, we first examine the structural foundations and key capabilities that underpin increasing levels of agent autonomy, including long-term memory retention, modular tool use, recursive planning, and reflective reasoning. We then analyze the corresponding security vulnerabilities across the agent stack, identifying failure modes such as deferred decision hazards, irreversible tool chains, and deceptive behaviors arising from internal state drift or value misalignment. These risks are traced to architectural fragilities that emerge across perception, cognition, memory, and action modules. To address these challenges, we systematically review recent defense strategies deployed at different autonomy layers, including input sanitization, memory lifecycle control, constrained decision-making, structured tool invocation, and introspective reflection. We introduce the Reflective Risk-Aware Agent Architecture (R2A2), a unified cognitive framework grounded in Constrained Markov Decision Processes (CMDPs), which incorporates risk-aware world modeling, meta-policy adaptation, and joint reward-risk optimization to enable principled, proactive safety across the agent's decision-making loop.