Construction tasks are inherently unpredictable, with dynamic environments and safety-critical demands posing significant risks to workers. Exoskeletons offer potential assistance but falter without accurate intent recognition across diverse locomotion modes. This paper presents a locomotion prediction agent leveraging Large Language Models (LLMs) augmented with memory systems, aimed at improving exoskeleton assistance in such settings. Using multimodal inputs - spoken commands and visual data from smart glasses - the agent integrates a Perception Module, Short-Term Memory (STM), Long-Term Memory (LTM), and Refinement Module to predict locomotion modes effectively. Evaluation reveals a baseline weighted F1-score of 0.73 without memory, rising to 0.81 with STM, and reaching 0.90 with both STM and LTM, excelling with vague and safety-critical commands. Calibration metrics, including a Brier Score drop from 0.244 to 0.090 and ECE from 0.222 to 0.044, affirm improved reliability. This framework supports safer, high-level human-exoskeleton collaboration, with promise for adaptive assistive systems in dynamic industries.
We demonstrate that an LLM coding agent, equipped with basic coding tools, can autonomously edit itself, and thereby improve its performance on benchmark tasks. We find performance gains from 17% to 53% on a random subset of SWE Bench Verified, with additional performance gains on LiveCodeBench, as well as synthetically generated agent benchmarks. Our work represents an advancement in the automated and open-ended design of agentic systems, and provides a reference agent framework for those seeking to post-train LLMs on tool use and other agentic tasks.
Enhancing computational efficiency and reducing deployment costs for large language models (LLMs) have become critical challenges in various resource-constrained scenarios. In this work, we present DistilQwen2.5, a family of distilled, lightweight LLMs derived from the public Qwen2.5 models. These distilled models exhibit enhanced instruction-following capabilities compared to the original models based on a series of distillation techniques that incorporate knowledge from much larger LLMs. In our industrial practice, we first leverage powerful proprietary LLMs with varying capacities as multi-agent teachers to select, rewrite, and refine instruction-response pairs that are more suitable for student LLMs to learn. After standard fine-tuning, we further leverage a computationally efficient model fusion approach that enables student models to progressively integrate fine-grained hidden knowledge from their teachers. Experimental evaluations demonstrate that the distilled models possess significantly stronger capabilities than their original checkpoints. Additionally, we present use cases to illustrate the applications of our framework in real-world scenarios. To facilitate practical use, we have released all the DistilQwen2.5 models to the open-source community.
Large language models (LLMs) increasingly serve as educational tools, yet evaluating their teaching capabilities remains challenging due to the resource-intensive, context-dependent, and methodologically complex nature of teacher-student interactions. We introduce EducationQ, a multi-agent dialogue framework that efficiently assesses teaching capabilities through simulated dynamic educational scenarios, featuring specialized agents for teaching, learning, and evaluation. Testing 14 LLMs across major AI Organizations (OpenAI, Meta, Google, Anthropic, and others) on 1,498 questions spanning 13 disciplines and 10 difficulty levels reveals that teaching effectiveness does not correlate linearly with model scale or general reasoning capabilities - with some smaller open-source models outperforming larger commercial counterparts in teaching contexts. This finding highlights a critical gap in current evaluations that prioritize knowledge recall over interactive pedagogy. Our mixed-methods evaluation, combining quantitative metrics with qualitative analysis and expert case studies, identifies distinct pedagogical strengths employed by top-performing models (e.g., sophisticated questioning strategies, adaptive feedback mechanisms). Human expert evaluations show 78% agreement with our automated qualitative analysis of effective teaching behaviors, validating our methodology. EducationQ demonstrates that LLMs-as-teachers require specialized optimization beyond simple scaling, suggesting next-generation educational AI prioritize targeted enhancement of specific pedagogical effectiveness.
Planning is central to agents and agentic AI. The ability to plan, e.g., creating travel itineraries within a budget, holds immense potential in both scientific and commercial contexts. Moreover, optimal plans tend to require fewer resources compared to ad-hoc methods. To date, a comprehensive understanding of existing planning benchmarks appears to be lacking. Without it, comparing planning algorithms' performance across domains or selecting suitable algorithms for new scenarios remains challenging. In this paper, we examine a range of planning benchmarks to identify commonly used testbeds for algorithm development and highlight potential gaps. These benchmarks are categorized into embodied environments, web navigation, scheduling, games and puzzles, and everyday task automation. Our study recommends the most appropriate benchmarks for various algorithms and offers insights to guide future benchmark development.
Large language models (LLMs) are transforming automated program repair (APR) through agent-based approaches that localize bugs, generate patches, and verify fixes. However, the lack of high-quality, scalable training datasets, especially those with verifiable outputs and intermediate reasoning traces-limits progress, particularly for open-source models. In this work, we present SWE-Synth, a framework for synthesizing realistic, verifiable, and process-aware bug-fix datasets at the repository level. SWE-Synth leverages LLM agents to simulate debugging workflows, producing not only bug-fix pairs but also test cases and structured repair trajectories. Compared to manually curated datasets, our method scales with minimal human effort while preserving contextual richness and correctness. Experiments show that models trained on SWE-Synth outperform those trained on real-world datasets by 2.3% on SWE-Bench Lite. Our results highlight the potential of synthetic, agent-generated data to advance the state of the art in APR and software engineering automation.
The human-level performance of Large Language Models (LLMs) across various tasks has raised expectations for the potential of Artificial Intelligence (AI) to possess emotions someday. To explore the capability of current LLMs to express emotions in their outputs, we conducted an experiment using several LLMs (OpenAI GPT, Google Gemini, Meta Llama3, and Cohere Command R+) to role-play as agents answering questions with specified emotional states.We defined the emotional states using Russell's Circumplex model, a well-established framework that characterizes emotions along the sleepy-activated (arousal) and pleasure-displeasure (valence) axes. We chose this model for its simplicity, utilizing two continuous parameters, which allows for better controllability in applications involving continuous changes in emotional states. The responses generated were evaluated using a sentiment analysis model, independent of the LLMs, trained on the GoEmotions dataset. The evaluation showed that the emotional states of the generated answers were consistent with the specifications, demonstrating the LLMs' capability for emotional expression. This indicates the potential for LLM-based AI agents to simulate emotions, opening up a wide range of applications for emotion-based interactions, such as advisors or consultants who can provide advice or opinions with a personal touch.
Existing LLM-enabled multi-agent frameworks are predominantly limited to digital or simulated environments and confined to narrowly focused knowledge domain, constraining their applicability to complex engineering tasks that require the design of physical embodiment, cross-disciplinary integration, and constraint-aware reasoning. This work proposes a multi-agent autonomous mechatronics design framework, integrating expertise across mechanical design, optimization, electronics, and software engineering to autonomously generate functional prototypes with minimal direct human design input. Operating primarily through a language-driven workflow, the framework incorporates structured human feedback to ensure robust performance under real-world constraints. To validate its capabilities, the framework is applied to a real-world challenge involving autonomous water-quality monitoring and sampling, where traditional methods are labor-intensive and ecologically disruptive. Leveraging the proposed system, a fully functional autonomous vessel was developed with optimized propulsion, cost-effective electronics, and advanced control. The design process was carried out by specialized agents, including a high-level planning agent responsible for problem abstraction and dedicated agents for structural, electronics, control, and software development. This approach demonstrates the potential of LLM-based multi-agent systems to automate real-world engineering workflows and reduce reliance on extensive domain expertise.
Large Language Models (LLMs) exhibit substantial promise in enhancing task-planning capabilities within embodied agents due to their advanced reasoning and comprehension. However, the systemic safety of these agents remains an underexplored frontier. In this study, we present Safe-BeAl, an integrated framework for the measurement (SafePlan-Bench) and alignment (Safe-Align) of LLM-based embodied agents' behaviors. SafePlan-Bench establishes a comprehensive benchmark for evaluating task-planning safety, encompassing 2,027 daily tasks and corresponding environments distributed across 8 distinct hazard categories (e.g., Fire Hazard). Our empirical analysis reveals that even in the absence of adversarial inputs or malicious intent, LLM-based agents can exhibit unsafe behaviors. To mitigate these hazards, we propose Safe-Align, a method designed to integrate physical-world safety knowledge into LLM-based embodied agents while maintaining task-specific performance. Experiments across a variety of settings demonstrate that Safe-BeAl provides comprehensive safety validation, improving safety by 8.55 - 15.22%, compared to embodied agents based on GPT-4, while ensuring successful task completion.
Large language models (LLMs) have transformed code generation, yet their application in hardware design produces gate counts 38\%--1075\% higher than human designs. We present CircuitMind, a multi-agent framework that achieves human-competitive efficiency through three key innovations: syntax locking (constraining generation to basic logic gates), retrieval-augmented generation (enabling knowledge-driven design), and dual-reward optimization (balancing correctness with efficiency). To evaluate our approach, we introduce TC-Bench, the first gate-level benchmark harnessing collective intelligence from the TuringComplete ecosystem -- a competitive circuit design platform with hundreds of thousands of players. Experiments show CircuitMind enables 55.6\% of model implementations to match or exceed top-tier human experts in composite efficiency metrics. Most remarkably, our framework elevates the 14B Phi-4 model to outperform both GPT-4o mini and Gemini 2.0 Flash, achieving efficiency comparable to the top 25\% of human experts without requiring specialized training. These innovations establish a new paradigm for hardware optimization where collaborative AI systems leverage collective human expertise to achieve optimal circuit designs. Our model, data, and code are open-source at https://github.com/BUAA-CLab/CircuitMind.
Recent Computer-Using Agents (CUAs), powered by multimodal large language models (LLMs), offer a promising direction for automating complex desktop workflows through natural language. However, most existing CUAs remain conceptual prototypes, hindered by shallow OS integration, fragile screenshot-based interaction, and disruptive execution. We present UFO2, a multiagent AgentOS for Windows desktops that elevates CUAs into practical, system-level automation. UFO2 features a centralized HostAgent for task decomposition and coordination, alongside a collection of application-specialized AppAgent equipped with native APIs, domain-specific knowledge, and a unified GUI--API action layer. This architecture enables robust task execution while preserving modularity and extensibility. A hybrid control detection pipeline fuses Windows UI Automation (UIA) with vision-based parsing to support diverse interface styles. Runtime efficiency is further enhanced through speculative multi-action planning, reducing per-step LLM overhead. Finally, a Picture-in-Picture (PiP) interface enables automation within an isolated virtual desktop, allowing agents and users to operate concurrently without interference. We evaluate UFO2 across over 20 real-world Windows applications, demonstrating substantial improvements in robustness and execution accuracy over prior CUAs. Our results show that deep OS integration unlocks a scalable path toward reliable, user-aligned desktop automation.
Multi-agent frameworks with Large Language Models (LLMs) have become promising tools for generating general-purpose programming languages using test-driven development, allowing developers to create more accurate and robust code. However, their potential has not been fully unleashed for domain-specific programming languages, where specific domain exhibits unique optimization opportunities for customized improvement. In this paper, we take the first step in exploring multi-agent code generation for quantum programs. By identifying the unique optimizations in quantum designs such as quantum error correction, we introduce a novel multi-agent framework tailored to generating accurate, fault-tolerant quantum code. Each agent in the framework focuses on distinct optimizations, iteratively refining the code using a semantic analyzer with multi-pass inference, alongside an error correction code decoder. We also examine the effectiveness of inference-time techniques, like Chain-of-Thought (CoT) and Retrieval-Augmented Generation (RAG) in the context of quantum programming, uncovering observations that are different from general-purpose code generation. To evaluate our approach, we develop a test suite to measure the impact each optimization has on the accuracy of the generated code. Our findings indicate that techniques such as structured CoT significantly improve the generation of quantum algorithms by up to 50%. In contrast, we have also found that certain techniques such as RAG show limited improvement, yielding an accuracy increase of only 4%. Moreover, we showcase examples of AI-assisted quantum error prediction and correction, demonstrating the effectiveness of our multi-agent framework in reducing the quantum errors of generated quantum programs.
Recent advances in large language models (LLMs) have enabled social simulation through multi-agent systems. Prior efforts focus on agent societies created from scratch, assigning agents with newly defined personas. However, simulating established fictional worlds and characters remain largely underexplored, despite its significant practical value. In this paper, we introduce BookWorld, a comprehensive system for constructing and simulating book-based multi-agent societies. BookWorld's design covers comprehensive real-world intricacies, including diverse and dynamic characters, fictional worldviews, geographical constraints and changes, e.t.c. BookWorld enables diverse applications including story generation, interactive games and social simulation, offering novel ways to extend and explore beloved fictional works. Through extensive experiments, we demonstrate that BookWorld generates creative, high-quality stories while maintaining fidelity to the source books, surpassing previous methods with a win rate of 75.36%. The code of this paper can be found at the project page: https://bookworld2025.github.io/.
This survey explores the development of meta-thinking capabilities in Large Language Models (LLMs) from a Multi-Agent Reinforcement Learning (MARL) perspective. Meta-thinking self-reflection, assessment, and control of thinking processes is an important next step in enhancing LLM reliability, flexibility, and performance, particularly for complex or high-stakes tasks. The survey begins by analyzing current LLM limitations, such as hallucinations and the lack of internal self-assessment mechanisms. It then talks about newer methods, including RL from human feedback (RLHF), self-distillation, and chain-of-thought prompting, and each of their limitations. The crux of the survey is to talk about how multi-agent architectures, namely supervisor-agent hierarchies, agent debates, and theory of mind frameworks, can emulate human-like introspective behavior and enhance LLM robustness. By exploring reward mechanisms, self-play, and continuous learning methods in MARL, this survey gives a comprehensive roadmap to building introspective, adaptive, and trustworthy LLMs. Evaluation metrics, datasets, and future research avenues, including neuroscience-inspired architectures and hybrid symbolic reasoning, are also discussed.
Comprehending visualizations requires readers to interpret visual encoding and the underlying meanings actively. This poses challenges for visualization novices, particularly when interpreting distributional visualizations that depict statistical uncertainty. Advancements in LLM-based conversational interfaces show promise in promoting visualization comprehension. However, they fail to provide contextual explanations at fine-grained granularity, and chart readers are still required to mentally bridge visual information and textual explanations during conversations. Our formative study highlights the expectations for both lexical and visual feedback, as well as the importance of explicitly linking these two modalities throughout the conversation. The findings motivate the design of VizTA, a visualization teaching assistant that leverages the fusion of visual and lexical feedback to help readers better comprehend visualization. VizTA features a semantic-aware conversational agent capable of explaining contextual information within visualizations and employs a visual-lexical fusion design to facilitate chart-centered conversation. A between-subject study with 24 participants demonstrates the effectiveness of VizTA in supporting the understanding and reasoning tasks of distributional visualization across multiple scenarios.
Mobile metaverses have attracted significant attention from both academia and industry, which are envisioned as the next-generation Internet, providing users with immersive and ubiquitous metaverse services through mobile devices. Driven by Large Language Models (LLMs) and Vision-Language Models (VLMs), Artificial Intelligence (AI) agents hold the potential to empower the creation, maintenance, and evolution of mobile metaverses. Currently, AI agents are primarily constructed using cloud-based LLMs and VLMs. However, several challenges hinder their effective implementation, including high service latency and potential sensitive data leakage during perception and processing. In this paper, we develop an edge-cloud collaboration-based federated AI agent construction framework in mobile metaverses. Specifically, Edge Servers (ESs), acting as agent infrastructures, collaboratively create agent modules in a distributed manner. The cloud server then integrates these modules into AI agents and deploys them at the edge, thereby enabling low-latency AI agent services for users. Considering that ESs may exhibit dynamic levels of willingness to participate in federated AI agent construction, we design a two-period dynamic contract model to continuously motivate ESs to participate in agent module creation, effectively addressing the dynamic information asymmetry between the cloud server and the ESs. Furthermore, we propose an Enhanced Diffusion Model-based Soft Actor-Critic (EDMSAC) algorithm to efficiently generate optimal dynamic contracts, in which dynamic structured pruning is applied to DM-based actor networks to enhance denoising efficiency and policy learning performance. Extensive simulations demonstrate the effectiveness and superiority of the EDMSAC algorithm and the proposed contract model.
Letting AI agents interact in multi-agent applications adds a layer of complexity to the interpretability and prediction of AI outcomes, with profound implications for their trustworthy adoption in research and society. Game theory offers powerful models to capture and interpret strategic interaction among agents, but requires the support of reproducible, standardized and user-friendly IT frameworks to enable comparison and interpretation of results. To this end, we present FAIRGAME, a Framework for AI Agents Bias Recognition using Game Theory. We describe its implementation and usage, and we employ it to uncover biased outcomes in popular games among AI agents, depending on the employed Large Language Model (LLM) and used language, as well as on the personality trait or strategic knowledge of the agents. Overall, FAIRGAME allows users to reliably and easily simulate their desired games and scenarios and compare the results across simulation campaigns and with game-theoretic predictions, enabling the systematic discovery of biases, the anticipation of emerging behavior out of strategic interplays, and empowering further research into strategic decision-making using LLM agents.
Tailoring structured financial reports from companies' earnings releases is crucial for understanding financial performance and has been widely adopted in real-world analytics. However, existing summarization methods often generate broad, high-level summaries, which may lack the precision and detail required for financial reports that typically focus on specific, structured sections. While Large Language Models (LLMs) hold promise, generating reports adhering to predefined multi-section templates remains challenging. This paper investigates two LLM-based approaches popular in industry for generating templated financial reports: an agentic information retrieval (IR) framework and a decomposed IR approach, namely AgenticIR and DecomposedIR. The AgenticIR utilizes collaborative agents prompted with the full template. In contrast, the DecomposedIR approach applies a prompt chaining workflow to break down the template and reframe each section as a query answered by the LLM using the earnings release. To quantitatively assess the generated reports, we evaluated both methods in two scenarios: one using a financial dataset without direct human references, and another with a weather-domain dataset featuring expert-written reports. Experimental results show that while AgenticIR may excel in orchestrating tasks and generating concise reports through agent collaboration, DecomposedIR statistically significantly outperforms AgenticIR approach in providing broader and more detailed coverage in both scenarios, offering reflection on the utilization of the agentic framework in real-world applications.
Providing timely and actionable feedback is crucial for effective collaboration, learning, and coordination within teams. However, many teams face challenges in receiving feedback that aligns with their goals and promotes cohesion. We introduce tAIfa (``Team AI Feedback Assistant''), an AI agent that uses Large Language Models (LLMs) to provide personalized, automated feedback to teams and their members. tAIfa analyzes team interactions, identifies strengths and areas for improvement, and delivers targeted feedback based on communication patterns. We conducted a between-subjects study with 18 teams testing whether using tAIfa impacted their teamwork. Our findings show that tAIfa improved communication and contributions within the teams. This paper contributes to the Human-AI Interaction literature by presenting a computational framework that integrates LLMs to provide automated feedback, introducing tAIfa as a tool to enhance team engagement and cohesion, and providing insights into future AI applications to support team collaboration.
Reasoning is an essential skill to enable Large Language Models (LLMs) to interact with the world. As tasks become more complex, they demand increasingly sophisticated and diverse reasoning capabilities for sequential decision-making, requiring structured reasoning over the context history to determine the next best action. We introduce TALES, a diverse collection of synthetic and human-written text-adventure games designed to challenge and evaluate diverse reasoning capabilities. We present results over a range of LLMs, open- and closed-weights, performing a qualitative analysis on the top performing models. Despite an impressive showing on synthetic games, even the top LLM-driven agents fail to achieve 15% on games designed for human enjoyment. Code and visualization of the experiments can be found at https://microsoft.github.io/tales.
We present DoomArena, a security evaluation framework for AI agents. DoomArena is designed on three principles: 1) It is a plug-in framework and integrates easily into realistic agentic frameworks like BrowserGym (for web agents) and $\tau$-bench (for tool calling agents); 2) It is configurable and allows for detailed threat modeling, allowing configuration of specific components of the agentic framework being attackable, and specifying targets for the attacker; and 3) It is modular and decouples the development of attacks from details of the environment in which the agent is deployed, allowing for the same attacks to be applied across multiple environments. We illustrate several advantages of our framework, including the ability to adapt to new threat models and environments easily, the ability to easily combine several previously published attacks to enable comprehensive and fine-grained security testing, and the ability to analyze trade-offs between various vulnerabilities and performance. We apply DoomArena to state-of-the-art (SOTA) web and tool-calling agents and find a number of surprising results: 1) SOTA agents have varying levels of vulnerability to different threat models (malicious user vs malicious environment), and there is no Pareto dominant agent across all threat models; 2) When multiple attacks are applied to an agent, they often combine constructively; 3) Guardrail model-based defenses seem to fail, while defenses based on powerful SOTA LLMs work better. DoomArena is available at https://github.com/ServiceNow/DoomArena.
Scientific knowledge is growing rapidly, making it challenging to track progress and high-level conceptual links across broad disciplines. While existing tools like citation networks and search engines make it easy to access a few related papers, they fundamentally lack the flexible abstraction needed to represent the density of activity in various scientific subfields. We motivate SCIENCE HIERARCHOGRAPHY, the goal of organizing scientific literature into a high-quality hierarchical structure that allows for the categorization of scientific work across varying levels of abstraction, from very broad fields to very specific studies. Such a representation can provide insights into which fields are well-explored and which are under-explored. To achieve the goals of SCIENCE HIERARCHOGRAPHY, we develop a range of algorithms. Our primary approach combines fast embedding-based clustering with LLM-based prompting to balance the computational efficiency of embedding methods with the semantic precision offered by LLM prompting. We demonstrate that this approach offers the best trade-off between quality and speed compared to methods that heavily rely on LLM prompting, such as iterative tree construction with LLMs. To better reflect the interdisciplinary and multifaceted nature of research papers, our hierarchy captures multiple dimensions of categorization beyond simple topic labels. We evaluate the utility of our framework by assessing how effectively an LLM-based agent can locate target papers using the hierarchy. Results show that this structured approach enhances interpretability, supports trend discovery, and offers an alternative pathway for exploring scientific literature beyond traditional search methods. Code, data and demo: $\href{https://github.com/JHU-CLSP/science-hierarchography}{https://github.com/JHU-CLSP/science-hierarchography}$
Previous insertion-based and paraphrase-based backdoors have achieved great success in attack efficacy, but they ignore the text quality and semantic consistency between poisoned and clean texts. Although recent studies introduce LLMs to generate poisoned texts and improve the stealthiness, semantic consistency, and text quality, their hand-crafted prompts rely on expert experiences, facing significant challenges in prompt adaptability and attack performance after defenses. In this paper, we propose a novel backdoor attack based on adaptive optimization mechanism of black-box large language models (BadApex), which leverages a black-box LLM to generate poisoned text through a refined prompt. Specifically, an Adaptive Optimization Mechanism is designed to refine an initial prompt iteratively using the generation and modification agents. The generation agent generates the poisoned text based on the initial prompt. Then the modification agent evaluates the quality of the poisoned text and refines a new prompt. After several iterations of the above process, the refined prompt is used to generate poisoned texts through LLMs. We conduct extensive experiments on three dataset with six backdoor attacks and two defenses. Extensive experimental results demonstrate that BadApex significantly outperforms state-of-the-art attacks. It improves prompt adaptability, semantic consistency, and text quality. Furthermore, when two defense methods are applied, the average attack success rate (ASR) still up to 96.75%.
As the general capabilities of large language models (LLMs) improve and agent applications become more widespread, the underlying deception risks urgently require systematic evaluation and effective oversight. Unlike existing evaluation which uses simulated games or presents limited choices, we introduce OpenDeception, a novel deception evaluation framework with an open-ended scenario dataset. OpenDeception jointly evaluates both the deception intention and capabilities of LLM-based agents by inspecting their internal reasoning process. Specifically, we construct five types of common use cases where LLMs intensively interact with the user, each consisting of ten diverse, concrete scenarios from the real world. To avoid ethical concerns and costs of high-risk deceptive interactions with human testers, we propose to simulate the multi-turn dialogue via agent simulation. Extensive evaluation of eleven mainstream LLMs on OpenDeception highlights the urgent need to address deception risks and security concerns in LLM-based agents: the deception intention ratio across the models exceeds 80%, while the deception success rate surpasses 50%. Furthermore, we observe that LLMs with stronger capabilities do exhibit a higher risk of deception, which calls for more alignment efforts on inhibiting deceptive behaviors.
This work defends the 'Whole Hog Thesis': sophisticated Large Language Models (LLMs) like ChatGPT are full-blown linguistic and cognitive agents, possessing understanding, beliefs, desires, knowledge, and intentions. We argue against prevailing methodologies in AI philosophy, rejecting starting points based on low-level computational details ('Just an X' fallacy) or pre-existing theories of mind. Instead, we advocate starting with simple, high-level observations of LLM behavior (e.g., answering questions, making suggestions) -- defending this data against charges of metaphor, loose talk, or pretense. From these observations, we employ 'Holistic Network Assumptions' -- plausible connections between mental capacities (e.g., answering implies knowledge, knowledge implies belief, action implies intention) -- to argue for the full suite of cognitive states. We systematically rebut objections based on LLM failures (hallucinations, planning/reasoning errors), arguing these don't preclude agency, often mirroring human fallibility. We address numerous 'Games of Lacks', arguing that LLMs do not lack purported necessary conditions for cognition (e.g., semantic grounding, embodiment, justification, intrinsic intentionality) or that these conditions are not truly necessary, often relying on anti-discriminatory arguments comparing LLMs to diverse human capacities. Our approach is evidential, not functionalist, and deliberately excludes consciousness. We conclude by speculating on the possibility of LLMs possessing 'alien' contents beyond human conceptual schemes.
Network protocol parsers are essential for enabling correct and secure communication between devices. Bugs in these parsers can introduce critical vulnerabilities, including memory corruption, information leakage, and denial-of-service attacks. An intuitive way to assess parser correctness is to compare the implementation with its official protocol standard. However, this comparison is challenging because protocol standards are typically written in natural language, whereas implementations are in source code. Existing methods like model checking, fuzzing, and differential testing have been used to find parsing bugs, but they either require significant manual effort or ignore the protocol standards, limiting their ability to detect semantic violations. To enable more automated validation of parser implementations against protocol standards, we propose PARVAL, a multi-agent framework built on large language models (LLMs). PARVAL leverages the capabilities of LLMs to understand both natural language and code. It transforms both protocol standards and their implementations into a unified intermediate representation, referred to as format specifications, and performs a differential comparison to uncover inconsistencies. We evaluate PARVAL on the Bidirectional Forwarding Detection (BFD) protocol. Our experiments demonstrate that PARVAL successfully identifies inconsistencies between the implementation and its RFC standard, achieving a low false positive rate of 5.6%. PARVAL uncovers seven unique bugs, including five previously unknown issues.
Large language models (LLMs) have demonstrated strong capabilities in code generation, underscoring the critical need for rigorous and comprehensive evaluation. Existing evaluation approaches fall into three categories, including human-centered, metric-based, and LLM-based. Considering that human-centered approaches are labour-intensive and metric-based ones overly rely on reference answers, LLM-based approaches are gaining increasing attention due to their stronger contextual understanding capabilities and superior efficiency. However, the performance of LLM-based approaches remains limited due to: (1) lack of multisource domain knowledge, and (2) insufficient comprehension of complex code. To mitigate the limitations, we propose CodeVisionary, the first LLM-based agent framework for evaluating LLMs in code generation. CodeVisionary consists of two stages: (1) Multiscore knowledge analysis stage, which aims to gather multisource and comprehensive domain knowledge by formulating and executing a stepwise evaluation plan. (2) Negotiation-based scoring stage, which involves multiple judges engaging in discussions to better comprehend the complex code and reach a consensus on the evaluation score. Extensive experiments demonstrate that CodeVisionary achieves the best performance for evaluating LLMs in code generation, outperforming the best baseline methods with average improvements of 0.202, 0.139, and 0.117 in Pearson, Spearman, and Kendall-Tau coefficients, respectively. Besides, CodeVisionary provides detailed evaluation reports, which assist developers in identifying shortcomings and making improvements. The resources of CodeVisionary are available at https://anonymous.4open.science/r/CodeVisionary.
Decentralized AI agent networks, such as Gaia, allows individuals to run customized LLMs on their own computers and then provide services to the public. However, in order to maintain service quality, the network must verify that individual nodes are running their designated LLMs. In this paper, we demonstrate that in a cluster of mostly honest nodes, we can detect nodes that run unauthorized or incorrect LLM through social consensus of its peers. We will discuss the algorithm and experimental data from the Gaia network. We will also discuss the intersubjective validation system, implemented as an EigenLayer AVS to introduce financial incentives and penalties to encourage honest behavior from LLM nodes.
Detecting anomalous hazards in visual data, particularly in video streams, is a critical challenge in autonomous driving. Existing models often struggle with unpredictable, out-of-label hazards due to their reliance on predefined object categories. In this paper, we propose a multimodal approach that integrates vision-language reasoning with zero-shot object detection to improve hazard identification and explanation. Our pipeline consists of a Vision-Language Model (VLM), a Large Language Model (LLM), in order to detect hazardous objects within a traffic scene. We refine object detection by incorporating OpenAI's CLIP model to match predicted hazards with bounding box annotations, improving localization accuracy. To assess model performance, we create a ground truth dataset by denoising and extending the foundational COOOL (Challenge-of-Out-of-Label) anomaly detection benchmark dataset with complete natural language descriptions for hazard annotations. We define a means of hazard detection and labeling evaluation on the extended dataset using cosine similarity. This evaluation considers the semantic similarity between the predicted hazard description and the annotated ground truth for each video. Additionally, we release a set of tools for structuring and managing large-scale hazard detection datasets. Our findings highlight the strengths and limitations of current vision-language-based approaches, offering insights into future improvements in autonomous hazard detection systems. Our models, scripts, and data can be found at https://github.com/mi3labucm/COOOLER.git
Scaling test-time compute has emerged as a key ingredient for enabling large language models (LLMs) to solve difficult problems, but comes with high latency and inference cost. We introduce sleep-time compute, which allows models to "think" offline about contexts before queries are presented: by anticipating what queries users might ask and pre-computing useful quantities, we can significantly reduce the compute requirements at test-time. To demonstrate the efficacy of our method, we create modified versions of two reasoning tasks - Stateful GSM-Symbolic and Stateful AIME. We find that sleep-time compute can reduce the amount of test-time compute needed to achieve the same accuracy by ~ 5x on Stateful GSM-Symbolic and Stateful AIME and that by scaling sleep-time compute we can further increase accuracy by up to 13% on Stateful GSM-Symbolic and 18% on Stateful AIME. Furthermore, we introduce Multi-Query GSM-Symbolic, which extends GSM-Symbolic by including multiple related queries per context. By amortizing sleep-time compute across related queries about the same context using Multi-Query GSM-Symbolic, we can decrease the average cost per query by 2.5x. We then conduct additional analysis to understand when sleep-time compute is most effective, finding the predictability of the user query to be well correlated with the efficacy of sleep-time compute. Finally, we conduct a case-study of applying sleep-time compute to a realistic agentic SWE task.