The emergence of instruction-tuned large language models (LLMs) has advanced the field of dialogue systems, enabling both realistic user simulations and robust multi-turn conversational agents. However, existing research often evaluates these components in isolation-either focusing on a single user simulator or a specific system design-limiting the generalisability of insights across architectures and configurations. In this work, we propose clem todd (chat-optimized LLMs for task-oriented dialogue systems development), a flexible framework for systematically evaluating dialogue systems under consistent conditions. clem todd enables detailed benchmarking across combinations of user simulators and dialogue systems, whether existing models from literature or newly developed ones. It supports plug-and-play integration and ensures uniform datasets, evaluation metrics, and computational constraints. We showcase clem todd's flexibility by re-evaluating existing task-oriented dialogue systems within this unified setup and integrating three newly proposed dialogue systems into the same evaluation pipeline. Our results provide actionable insights into how architecture, scale, and prompting strategies affect dialogue performance, offering practical guidance for building efficient and effective conversational AI systems.
Cloud-based mobile agents powered by (multimodal) large language models ((M)LLMs) offer strong reasoning abilities but suffer from high latency and cost. While fine-tuned (M)SLMs enable edge deployment, they often lose general capabilities and struggle with complex tasks. To address this, we propose EcoAgent, an Edge-Cloud cOllaborative multi-agent framework for mobile automation. EcoAgent features a closed-loop collaboration among a cloud-based Planning Agent and two edge-based agents: the Execution Agent for action execution and the Observation Agent for verifying outcomes. The Observation Agent uses a Pre-Understanding Module to compress screen images into concise text, reducing token usage. In case of failure, the Planning Agent retrieves screen history and replans via a Reflection Module. Experiments on AndroidWorld show that EcoAgent maintains high task success rates while significantly reducing MLLM token consumption, enabling efficient and practical mobile automation.
Recent advances in leveraging the agentic paradigm of large language models (LLMs) utilization have significantly enhanced Text-to-SQL capabilities, enabling users without specialized database expertise to query data intuitively. However, deploying these agentic LLM-based Text-to-SQL systems in production poses substantial challenges due to their inherently multi-stage workflows, stringent latency constraints, and potentially heterogeneous GPU infrastructure in enterprise environments. Current LLM serving frameworks lack effective mechanisms for handling interdependent inference tasks, dynamic latency variability, and resource heterogeneity, leading to suboptimal performance and frequent service-level objective (SLO) violations. In this paper, we introduce HEXGEN-TEXT2SQL, a novel framework designed explicitly to schedule and execute agentic multi-stage LLM-based Text-to-SQL workflows on heterogeneous GPU clusters that handle multi-tenant end-to-end queries. HEXGEN-TEXT2SQL introduce a hierarchical scheduling approach combining global workload-balanced task dispatching and local adaptive urgency-guided prioritization, guided by a systematic analysis of agentic Text-to-SQL workflows. Additionally, we propose a lightweight simulation-based method for tuning critical scheduling hyperparameters, further enhancing robustness and adaptability. Our extensive evaluation on realistic Text-to-SQL benchmarks demonstrates that HEXGEN-TEXT2SQL significantly outperforms state-of-the-art LLM serving frameworks. Specifically, HEXGEN-TEXT2SQL reduces latency deadlines by up to 1.67$\times$ (average: 1.41$\times$) and improves system throughput by up to 1.75$\times$ (average: 1.65$\times$) compared to vLLM under diverse, realistic workload conditions. Our code is available at https://github.com/Relaxed-System-Lab/Hexgen-Flow.
Large Language Models (LLMs) assist in specialized tasks but struggle to align with evolving domain knowledge without costly fine-tuning. Domain knowledge consists of: Knowledge: Immutable facts (e.g., 'A stone is solid') and generally accepted principles (e.g., ethical standards); Refined Memory: Evolving insights shaped by business needs and real-world changes. However, a significant gap often exists between a domain expert's deep, nuanced understanding and the system's domain knowledge, which can hinder accurate information retrieval and application. Our Memory-Augmented Refinement of Knowledge (MARK) framework enables LLMs to continuously learn without retraining by leveraging structured refined memory, inspired by the Society of Mind. MARK operates through specialized agents, each serving a distinct role: Residual Refined Memory Agent: Stores and retrieves domain-specific insights to maintain context over time; User Question Refined Memory Agent: Captures user-provided facts, abbreviations, and terminology for better comprehension; LLM Response Refined Memory Agent: Extracts key elements from responses for refinement and personalization. These agents analyse stored refined memory, detect patterns, resolve contradictions, and improve response accuracy. Temporal factors like recency and frequency prioritize relevant information while discarding outdated insights. MARK enhances LLMs in multiple ways: Ground Truth Strategy: Reduces hallucinations by establishing a structured reference; Domain-Specific Adaptation: Essential for fields like healthcare, law, and manufacturing, where proprietary insights are absent from public datasets; Personalized AI Assistants: Improves virtual assistants by remembering user preferences, ensuring coherent responses over time.
Embodied artificial intelligence (Embodied AI) plays a pivotal role in the application of advanced technologies in the intelligent era, where AI systems are integrated with physical bodies that enable them to perceive, reason, and interact with their environments. Through the use of sensors for input and actuators for action, these systems can learn and adapt based on real-world feedback, allowing them to perform tasks effectively in dynamic and unpredictable environments. As techniques such as deep learning (DL), reinforcement learning (RL), and large language models (LLMs) mature, embodied AI has become a leading field in both academia and industry, with applications spanning robotics, healthcare, transportation, and manufacturing. However, most research has focused on single-agent systems that often assume static, closed environments, whereas real-world embodied AI must navigate far more complex scenarios. In such settings, agents must not only interact with their surroundings but also collaborate with other agents, necessitating sophisticated mechanisms for adaptation, real-time learning, and collaborative problem-solving. Despite increasing interest in multi-agent systems, existing research remains narrow in scope, often relying on simplified models that fail to capture the full complexity of dynamic, open environments for multi-agent embodied AI. Moreover, no comprehensive survey has systematically reviewed the advancements in this area. As embodied AI rapidly evolves, it is crucial to deepen our understanding of multi-agent embodied AI to address the challenges presented by real-world applications. To fill this gap and foster further development in the field, this paper reviews the current state of research, analyzes key contributions, and identifies challenges and future directions, providing insights to guide innovation and progress in this field.
Reasoning lies at the heart of intelligence, shaping the ability to make decisions, draw conclusions, and generalize across domains. In artificial intelligence, as systems increasingly operate in open, uncertain, and multimodal environments, reasoning becomes essential for enabling robust and adaptive behavior. Large Multimodal Reasoning Models (LMRMs) have emerged as a promising paradigm, integrating modalities such as text, images, audio, and video to support complex reasoning capabilities and aiming to achieve comprehensive perception, precise understanding, and deep reasoning. As research advances, multimodal reasoning has rapidly evolved from modular, perception-driven pipelines to unified, language-centric frameworks that offer more coherent cross-modal understanding. While instruction tuning and reinforcement learning have improved model reasoning, significant challenges remain in omni-modal generalization, reasoning depth, and agentic behavior. To address these issues, we present a comprehensive and structured survey of multimodal reasoning research, organized around a four-stage developmental roadmap that reflects the field's shifting design philosophies and emerging capabilities. First, we review early efforts based on task-specific modules, where reasoning was implicitly embedded across stages of representation, alignment, and fusion. Next, we examine recent approaches that unify reasoning into multimodal LLMs, with advances such as Multimodal Chain-of-Thought (MCoT) and multimodal reinforcement learning enabling richer and more structured reasoning chains. Finally, drawing on empirical insights from challenging benchmarks and experimental cases of OpenAI O3 and O4-mini, we discuss the conceptual direction of native large multimodal reasoning models (N-LMRMs), which aim to support scalable, agentic, and adaptive reasoning and planning in complex, real-world environments.
Producing large volumes of high-quality, timely feedback poses significant challenges to instructors. To address this issue, automation technologies-particularly Large Language Models (LLMs)-show great potential. However, current LLM-based research still shows room for improvement in terms of feedback quality. Our study proposed a multi-agent approach performing "generation, evaluation, and regeneration" (G-E-RG) to further enhance feedback quality. In the first-generation phase, six methods were adopted, combining three feedback theoretical frameworks and two prompt methods: zero-shot and retrieval-augmented generation with chain-of-thought (RAG_CoT). The results indicated that, compared to first-round feedback, G-E-RG significantly improved final feedback across six methods for most dimensions. Specifically:(1) Evaluation accuracy for six methods increased by 3.36% to 12.98% (p<0.001); (2) The proportion of feedback containing four effective components rose from an average of 27.72% to an average of 98.49% among six methods, sub-dimensions of providing critiques, highlighting strengths, encouraging agency, and cultivating dialogue also showed great enhancement (p<0.001); (3) There was a significant improvement in most of the feature values (p<0.001), although some sub-dimensions (e.g., strengthening the teacher-student relationship) still require further enhancement; (4) The simplicity of feedback was effectively enhanced (p<0.001) for three methods.
Fast and effective incident response is essential to prevent adversarial cyberattacks. Autonomous Cyber Defense (ACD) aims to automate incident response through Artificial Intelligence (AI) agents that plan and execute actions. Most ACD approaches focus on single-agent scenarios and leverage Reinforcement Learning (RL). However, ACD RL-trained agents depend on costly training, and their reasoning is not always explainable or transferable. Large Language Models (LLMs) can address these concerns by providing explainable actions in general security contexts. Researchers have explored LLM agents for ACD but have not evaluated them on multi-agent scenarios or interacting with other ACD agents. In this paper, we show the first study on how LLMs perform in multi-agent ACD environments by proposing a new integration to the CybORG CAGE 4 environment. We examine how ACD teams of LLM and RL agents can interact by proposing a novel communication protocol. Our results highlight the strengths and weaknesses of LLMs and RL and help us identify promising research directions to create, train, and deploy future teams of ACD agents.
Multi-agent collaboration systems (MACS), powered by large language models (LLMs), solve complex problems efficiently by leveraging each agent's specialization and communication between agents. However, the inherent exchange of information between agents and their interaction with external environments, such as LLM, tools, and users, inevitably introduces significant risks of sensitive data leakage, including vulnerabilities to attacks like prompt injection and reconnaissance. Existing MACS fail to enable privacy controls, making it challenging to manage sensitive information securely. In this paper, we take the first step to address the MACS's data leakage threat at the system development level through a privacy-enhanced development paradigm, Maris. Maris enables rigorous message flow control within MACS by embedding reference monitors into key multi-agent conversation components. We implemented Maris as an integral part of AutoGen, a widely adopted open-source multi-agent development framework. Then, we evaluate Maris for its effectiveness and performance overhead on privacy-critical MACS use cases, including healthcare, supply chain optimization, and personalized recommendation system. The result shows that Maris achieves satisfactory effectiveness, performance overhead and practicability for adoption.
The emergence of Generative AI (Gen AI) and Large Language Models (LLMs) has enabled more advanced chatbots capable of human-like interactions. However, these conversational agents introduce a broader set of operational risks that extend beyond traditional cybersecurity considerations. In this work, we propose a novel, instrumented risk-assessment metric that simultaneously evaluates potential threats to three key stakeholders: the service-providing organization, end users, and third parties. Our approach incorporates the technical complexity required to induce erroneous behaviors in the chatbot--ranging from non-induced failures to advanced prompt-injection attacks--as well as contextual factors such as the target industry, user age range, and vulnerability severity. To validate our metric, we leverage Garak, an open-source framework for LLM vulnerability testing. We further enhance Garak to capture a variety of threat vectors (e.g., misinformation, code hallucinations, social engineering, and malicious code generation). Our methodology is demonstrated in a scenario involving chatbots that employ retrieval-augmented generation (RAG), showing how the aggregated risk scores guide both short-term mitigation and longer-term improvements in model design and deployment. The results underscore the importance of multi-dimensional risk assessments in operationalizing secure, reliable AI-driven conversational systems.
Large Language Models (LLMs) show potential for complex reasoning, yet their capacity for emergent coordination in Multi-Agent Systems (MAS) when operating under strict constraints-such as limited local perception and communication, characteristic of natural swarms-remains largely unexplored, particularly concerning the nuances of swarm intelligence. Existing benchmarks often do not fully capture the unique challenges of decentralized coordination that arise when agents operate with incomplete spatio-temporal information. To bridge this gap, we introduce SwarmBench, a novel benchmark designed to systematically evaluate the swarm intelligence capabilities of LLMs acting as decentralized agents. SwarmBench features five foundational MAS coordination tasks within a configurable 2D grid environment, forcing agents to rely primarily on local sensory input (k x k view) and local communication. We propose metrics for coordination effectiveness and analyze emergent group dynamics. Evaluating several leading LLMs in a zero-shot setting, we find significant performance variations across tasks, highlighting the difficulties posed by local information constraints. While some coordination emerges, results indicate limitations in robust planning and strategy formation under uncertainty in these decentralized scenarios. Assessing LLMs under swarm-like conditions is crucial for realizing their potential in future decentralized systems. We release SwarmBench as an open, extensible toolkit-built upon a customizable and scalable physical system with defined mechanical properties. It provides environments, prompts, evaluation scripts, and the comprehensive experimental datasets generated, aiming to foster reproducible research into LLM-based MAS coordination and the theoretical underpinnings of Embodied MAS. Our code repository is available at https://github.com/x66ccff/swarmbench.
With open-source projects growing in size and complexity, manual compilation becomes tedious and error-prone, highlighting the need for automation to improve efficiency and accuracy. However, the complexity of compilation instruction search and error resolution makes automatic compilation challenging. Inspired by the success of LLM-based agents in various fields, we propose CompileAgent, the first LLM-based agent framework dedicated to repo-level compilation. CompileAgent integrates five tools and a flow-based agent strategy, enabling interaction with software artifacts for compilation instruction search and error resolution. To measure the effectiveness of our method, we design a public repo-level benchmark CompileAgentBench, and we also design two baselines for comparison by combining two compilation-friendly schemes. The performance on this benchmark shows that our method significantly improves the compilation success rate, ranging from 10% to 71%. Meanwhile, we evaluate the performance of CompileAgent under different agent strategies and verify the effectiveness of the flow-based strategy. Additionally, we emphasize the scalability of CompileAgent, further expanding its application prospects.
Multi-agent autonomous systems (MAS) are better at addressing challenges that spans across multiple domains than singular autonomous agents. This holds true within the field of software engineering (SE) as well. The state-of-the-art research on MAS within SE focuses on integrating LLMs at the core of autonomous agents to create LLM-based multi-agent autonomous (LMA) systems. However, the introduction of LMA systems into SE brings a plethora of challenges. One of the major challenges is the strategic allocation of tasks between humans and the LMA system in a trustworthy manner. To address this challenge, a RACI-based framework is proposed in this work in progress article, along with implementation guidelines and an example implementation of the framework. The proposed framework can facilitate efficient collaboration, ensure accountability, and mitigate potential risks associated with LLM-driven automation while aligning with the Trustworthy AI guidelines. The future steps for this work delineating the planned empirical validation method are also presented.
Large Language Models (LLMs) have emerged as promising tools in software development, enabling automated code generation and analysis. However, their knowledge is limited to a fixed cutoff date, making them prone to generating code vulnerable to newly disclosed CVEs. Frequent fine-tuning with new CVE sets is costly, and existing LLM-based approaches focus on oversimplified CWE examples and require providing explicit bug locations to LLMs, limiting their ability to patch complex real-world vulnerabilities. To address these limitations, we propose AutoPatch, a multi-agent framework designed to patch vulnerable LLM-generated code, particularly those introduced after the LLMs' knowledge cutoff. AutoPatch integrates Retrieval-Augmented Generation (RAG) with a structured database of recently disclosed vulnerabilities, comprising 525 code snippets derived from 75 high-severity CVEs across real-world systems such as the Linux kernel and Chrome. AutoPatch combines semantic and taint analysis to identify the most relevant CVE and leverages enhanced Chain-of-Thought (CoT) reasoning to construct enriched prompts for verification and patching. Our unified similarity model, which selects the most relevant vulnerabilities, achieves 90.4 percent accuracy in CVE matching. AutoPatch attains 89.5 percent F1-score for vulnerability verification and 95.0 percent accuracy in patching, while being over 50x more cost-efficient than traditional fine-tuning approaches.
Redundant code is a persistent challenge in software development that makes systems harder to maintain, scale, and update. It adds unnecessary complexity, hinders bug fixes, and increases technical debt. Despite their impact, removing redundant code manually is risky and error-prone, often introducing new bugs or missing dependencies. While studies highlight the prevalence and negative impact of redundant code, little focus has been given to Artificial Intelligence (AI) system codebases and the common patterns that cause redundancy. Additionally, the reasons behind developers unintentionally introducing redundant code remain largely unexplored. This research addresses these gaps by leveraging large language models (LLMs) to automatically detect and optimize redundant code in AI projects. Our research aims to identify recurring patterns of redundancy and analyze their underlying causes, such as outdated practices or insufficient awareness of best coding principles. Additionally, we plan to propose an LLM agent that will facilitate the detection and refactoring of redundancies on a large scale while preserving original functionality. This work advances the application of AI in identifying and optimizing redundant code, ultimately helping developers maintain cleaner, more readable, and scalable codebases.
Structured outputs are essential for large language models (LLMs) in critical applications like agents and information extraction. Despite their capabilities, LLMs often generate outputs that deviate from predefined schemas, significantly hampering reliable application development. We present SLOT (Structured LLM Output Transformer), a model-agnostic approach that transforms unstructured LLM outputs into precise structured formats. While existing solutions predominantly rely on constrained decoding techniques or are tightly coupled with specific models, SLOT employs a fine-tuned lightweight language model as a post-processing layer, achieving flexibility across various LLMs and schema specifications. We introduce a systematic pipeline for data curation and synthesis alongside a formal evaluation methodology that quantifies both schema accuracy and content fidelity. Our results demonstrate that fine-tuned Mistral-7B model with constrained decoding achieves near perfect schema accuracy (99.5%) and content similarity (94.0%), outperforming Claude-3.5-Sonnet by substantial margins (+25 and +20 percentage points, respectively). Notably, even compact models like Llama-3.2-1B can match or exceed the structured output capabilities of much larger proprietary models when equipped with SLOT, enabling reliable structured generation in resource-constrained environments.
LLM-based optimization has shown remarkable potential in enhancing agentic systems. However, the conventional approach of prompting LLM optimizer with the whole training trajectories on training dataset in a single pass becomes untenable as datasets grow, leading to context window overflow and degraded pattern recognition. To address these challenges, we propose Fine-Grained Optimization (FGO), a scalable framework that divides large optimization tasks into manageable subsets, performs targeted optimizations, and systematically combines optimized components through progressive merging. Evaluation across ALFWorld, LogisticsQA, and GAIA benchmarks demonstrate that FGO outperforms existing approaches by 1.6-8.6% while reducing average prompt token consumption by 56.3%. Our framework provides a practical solution for scaling up LLM-based optimization of increasingly sophisticated agent systems. Further analysis demonstrates that FGO achieves the most consistent performance gain in all training dataset sizes, showcasing its scalability and efficiency.
According to Yuval Noah Harari, large-scale human cooperation is driven by shared narratives that encode common beliefs and values. This study explores whether such narratives can similarly nudge LLM agents toward collaboration. We use a finitely repeated public goods game in which LLM agents choose either cooperative or egoistic spending strategies. We prime agents with stories highlighting teamwork to different degrees and test how this influences negotiation outcomes. Our experiments explore four questions:(1) How do narratives influence negotiation behavior? (2) What differs when agents share the same story versus different ones? (3) What happens when the agent numbers grow? (4) Are agents resilient against self-serving negotiators? We find that story-based priming significantly affects negotiation strategies and success rates. Common stories improve collaboration, benefiting each agent. By contrast, priming agents with different stories reverses this effect, and those agents primed toward self-interest prevail. We hypothesize that these results carry implications for multi-agent system design and AI alignment.
One of the primary aspirations in reinforcement learning research is developing general-purpose agents capable of rapidly adapting to and mastering novel tasks. While RL gaming agents have mastered many Atari games, they remain slow and costly to train for each game. In this work, we demonstrate that latest reasoning LLMs with out-of-domain RL post-training can play a challenging Atari game called Frogger under a zero-shot setting. We then investigate the effect of in-context learning and the amount of reasoning effort on LLM performance. Lastly, we demonstrate a way to bootstrap traditional RL method with LLM demonstrations, which significantly improves their performance and sample efficiency. Our implementation is open sourced at https://github.com/AlienKevin/frogger.
Large Language Models (LLMs) are transforming scientific hypothesis generation and validation by enabling information synthesis, latent relationship discovery, and reasoning augmentation. This survey provides a structured overview of LLM-driven approaches, including symbolic frameworks, generative models, hybrid systems, and multi-agent architectures. We examine techniques such as retrieval-augmented generation, knowledge-graph completion, simulation, causal inference, and tool-assisted reasoning, highlighting trade-offs in interpretability, novelty, and domain alignment. We contrast early symbolic discovery systems (e.g., BACON, KEKADA) with modern LLM pipelines that leverage in-context learning and domain adaptation via fine-tuning, retrieval, and symbolic grounding. For validation, we review simulation, human-AI collaboration, causal modeling, and uncertainty quantification, emphasizing iterative assessment in open-world contexts. The survey maps datasets across biomedicine, materials science, environmental science, and social science, introducing new resources like AHTech and CSKG-600. Finally, we outline a roadmap emphasizing novelty-aware generation, multimodal-symbolic integration, human-in-the-loop systems, and ethical safeguards, positioning LLMs as agents for principled, scalable scientific discovery.
The automation of scientific research through large language models (LLMs) presents significant opportunities but faces critical challenges in knowledge synthesis and quality assurance. We introduce Feedback-Refined Agent Methodology (FRAME), a novel framework that enhances medical paper generation through iterative refinement and structured feedback. Our approach comprises three key innovations: (1) A structured dataset construction method that decomposes 4,287 medical papers into essential research components through iterative refinement; (2) A tripartite architecture integrating Generator, Evaluator, and Reflector agents that progressively improve content quality through metric-driven feedback; and (3) A comprehensive evaluation framework that combines statistical metrics with human-grounded benchmarks. Experimental results demonstrate FRAME's effectiveness, achieving significant improvements over conventional approaches across multiple models (9.91% average gain with DeepSeek V3, comparable improvements with GPT-4o Mini) and evaluation dimensions. Human evaluation confirms that FRAME-generated papers achieve quality comparable to human-authored works, with particular strength in synthesizing future research directions. The results demonstrated our work could efficiently assist medical research by building a robust foundation for automated medical research paper generation while maintaining rigorous academic standards.
Large language models (LLMs) have transformed software development through code generation capabilities, yet their effectiveness for high-performance computing (HPC) remains limited. HPC code requires specialized optimizations for parallelism, memory efficiency, and architecture-specific considerations that general-purpose LLMs often overlook. We present MARCO (Multi-Agent Reactive Code Optimizer), a novel framework that enhances LLM-generated code for HPC through a specialized multi-agent architecture. MARCO employs separate agents for code generation and performance evaluation, connected by a feedback loop that progressively refines optimizations. A key innovation is MARCO's web-search component that retrieves real-time optimization techniques from recent conference proceedings and research publications, bridging the knowledge gap in pre-trained LLMs. Our extensive evaluation on the LeetCode 75 problem set demonstrates that MARCO achieves a 14.6% average runtime reduction compared to Claude 3.5 Sonnet alone, while the integration of the web-search component yields a 30.9% performance improvement over the base MARCO system. These results highlight the potential of multi-agent systems to address the specialized requirements of high-performance code generation, offering a cost-effective alternative to domain-specific model fine-tuning.
LLM-based agents have demonstrated great potential in generating and managing code within complex codebases. In this paper, we introduce WebGen-Bench, a novel benchmark designed to measure an LLM-based agent's ability to create multi-file website codebases from scratch. It contains diverse instructions for website generation, created through the combined efforts of human annotators and GPT-4o. These instructions span three major categories and thirteen minor categories, encompassing nearly all important types of web applications. To assess the quality of the generated websites, we use GPT-4o to generate test cases targeting each functionality described in the instructions, and then manually filter, adjust, and organize them to ensure accuracy, resulting in 647 test cases. Each test case specifies an operation to be performed on the website and the expected result after the operation. To automate testing and improve reproducibility, we employ a powerful web-navigation agent to execute tests on the generated websites and determine whether the observed responses align with the expected results. We evaluate three high-performance code-agent frameworks, Bolt.diy, OpenHands, and Aider, using multiple proprietary and open-source LLMs as engines. The best-performing combination, Bolt.diy powered by DeepSeek-R1, achieves only 27.8\% accuracy on the test cases, highlighting the challenging nature of our benchmark. Additionally, we construct WebGen-Instruct, a training set consisting of 6,667 website-generation instructions. Training Qwen2.5-Coder-32B-Instruct on Bolt.diy trajectories generated from a subset of this training set achieves an accuracy of 38.2\%, surpassing the performance of the best proprietary model.
Large language models (LLMs) have evolved from simple chatbots into autonomous agents capable of performing complex tasks such as editing production code, orchestrating workflows, and taking higher-stakes actions based on untrusted inputs like webpages and emails. These capabilities introduce new security risks that existing security measures, such as model fine-tuning or chatbot-focused guardrails, do not fully address. Given the higher stakes and the absence of deterministic solutions to mitigate these risks, there is a critical need for a real-time guardrail monitor to serve as a final layer of defense, and support system level, use case specific safety policy definition and enforcement. We introduce LlamaFirewall, an open-source security focused guardrail framework designed to serve as a final layer of defense against security risks associated with AI Agents. Our framework mitigates risks such as prompt injection, agent misalignment, and insecure code risks through three powerful guardrails: PromptGuard 2, a universal jailbreak detector that demonstrates clear state of the art performance; Agent Alignment Checks, a chain-of-thought auditor that inspects agent reasoning for prompt injection and goal misalignment, which, while still experimental, shows stronger efficacy at preventing indirect injections in general scenarios than previously proposed approaches; and CodeShield, an online static analysis engine that is both fast and extensible, aimed at preventing the generation of insecure or dangerous code by coding agents. Additionally, we include easy-to-use customizable scanners that make it possible for any developer who can write a regular expression or an LLM prompt to quickly update an agent's security guardrails.
The 6G wireless communications aim to establish an intelligent world of ubiquitous connectivity, providing an unprecedented communication experience. Large artificial intelligence models (LAMs) are characterized by significantly larger scales (e.g., billions or trillions of parameters) compared to typical artificial intelligence (AI) models. LAMs exhibit outstanding cognitive abilities, including strong generalization capabilities for fine-tuning to downstream tasks, and emergent capabilities to handle tasks unseen during training. Therefore, LAMs efficiently provide AI services for diverse communication applications, making them crucial tools for addressing complex challenges in future wireless communication systems. This study provides a comprehensive review of the foundations, applications, and challenges of LAMs in communication. First, we introduce the current state of AI-based communication systems, emphasizing the motivation behind integrating LAMs into communications and summarizing the key contributions. We then present an overview of the essential concepts of LAMs in communication. This includes an introduction to the main architectures of LAMs, such as transformer, diffusion models, and mamba. We also explore the classification of LAMs, including large language models (LLMs), large vision models (LVMs), large multimodal models (LMMs), and world models, and examine their potential applications in communication. Additionally, we cover the training methods and evaluation techniques for LAMs in communication systems. Lastly, we introduce optimization strategies such as chain of thought (CoT), retrieval augmented generation (RAG), and agentic systems. Following this, we discuss the research advancements of LAMs across various communication scenarios. Finally, we analyze the challenges in the current research and provide insights into potential future research directions.
Inconsistent outputs and hallucinations from large language models (LLMs) are major obstacles to reliable AI systems. When different proprietary reasoning models (RMs), such as those by OpenAI, Google, Anthropic, DeepSeek, and xAI, are given the same complex request, they often produce divergent results due to variations in training and inference. This paper proposes a novel consensus mechanism, inspired by distributed ledger technology, to validate and converge these outputs, treating each RM as a black-box peer. Building on the Hashgraph consensus algorithm, our approach employs gossip-about-gossip communication and virtual voting to achieve agreement among an ensemble of RMs. We present an architectural design for a prototype system in which RMs iteratively exchange and update their answers, using information from each round to improve accuracy and confidence in subsequent rounds. This approach goes beyond simple majority voting by incorporating the knowledge and cross-verification content of every model. We justify the feasibility of this Hashgraph-inspired consensus for AI ensembles and outline its advantages over traditional ensembling techniques in reducing nonfactual outputs. Preliminary considerations for implementation, evaluation criteria for convergence and accuracy, and potential challenges are discussed. The proposed mechanism demonstrates a promising direction for multi-agent AI systems to self-validate and deliver high-fidelity responses in complex tasks.
The growing demand for intelligent logistics, particularly fine-grained terminal delivery, underscores the need for autonomous UAV (Unmanned Aerial Vehicle)-based delivery systems. However, most existing last-mile delivery studies rely on ground robots, while current UAV-based Vision-Language Navigation (VLN) tasks primarily focus on coarse-grained, long-range goals, making them unsuitable for precise terminal delivery. To bridge this gap, we propose LogisticsVLN, a scalable aerial delivery system built on multimodal large language models (MLLMs) for autonomous terminal delivery. LogisticsVLN integrates lightweight Large Language Models (LLMs) and Visual-Language Models (VLMs) in a modular pipeline for request understanding, floor localization, object detection, and action-decision making. To support research and evaluation in this new setting, we construct the Vision-Language Delivery (VLD) dataset within the CARLA simulator. Experimental results on the VLD dataset showcase the feasibility of the LogisticsVLN system. In addition, we conduct subtask-level evaluations of each module of our system, offering valuable insights for improving the robustness and real-world deployment of foundation model-based vision-language delivery systems.
The potential for large language models (LLMs) to hide messages within plain text (steganography) poses a challenge to detection and thwarting of unaligned AI agents, and undermines faithfulness of LLMs reasoning. We explore the steganographic capabilities of LLMs fine-tuned via reinforcement learning (RL) to: (1) develop covert encoding schemes, (2) engage in steganography when prompted, and (3) utilize steganography in realistic scenarios where hidden reasoning is likely, but not prompted. In these scenarios, we detect the intention of LLMs to hide their reasoning as well as their steganography performance. Our findings in the fine-tuning experiments as well as in behavioral non fine-tuning evaluations reveal that while current models exhibit rudimentary steganographic abilities in terms of security and capacity, explicit algorithmic guidance markedly enhances their capacity for information concealment.
Large Language Models (LLMs) represent a landmark achievement in Artificial Intelligence (AI), demonstrating unprecedented proficiency in procedural tasks such as text generation, code completion, and conversational coherence. These capabilities stem from their architecture, which mirrors human procedural memory -- the brain's ability to automate repetitive, pattern-driven tasks through practice. However, as LLMs are increasingly deployed in real-world applications, it becomes impossible to ignore their limitations operating in complex, unpredictable environments. This paper argues that LLMs, while transformative, are fundamentally constrained by their reliance on procedural memory. To create agents capable of navigating ``wicked'' learning environments -- where rules shift, feedback is ambiguous, and novelty is the norm -- we must augment LLMs with semantic memory and associative learning systems. By adopting a modular architecture that decouples these cognitive functions, we can bridge the gap between narrow procedural expertise and the adaptive intelligence required for real-world problem-solving.
Reinforcement learning from expert demonstrations has long remained a challenging research problem, and existing state-of-the-art methods using behavioral cloning plus further RL training often suffer from poor generalization, low sample efficiency, and poor model interpretability. Inspired by the strong reasoning abilities of large language models (LLMs), we propose a novel strategy-based reinforcement learning framework integrated with LLMs called DYnamic STrategy Induction with Llms for reinforcement learning (DYSTIL) to overcome these limitations. DYSTIL dynamically queries a strategy-generating LLM to induce textual strategies based on advantage estimations and expert demonstrations, and gradually internalizes induced strategies into the RL agent through policy optimization to improve its performance through boosting policy generalization and enhancing sample efficiency. It also provides a direct textual channel to observe and interpret the evolution of the policy's underlying strategies during training. We test DYSTIL over challenging RL environments from Minigrid and BabyAI, and empirically demonstrate that DYSTIL significantly outperforms state-of-the-art baseline methods by 17.75% in average success rate while also enjoying higher sample efficiency during the learning process.