Despite rapid advances in autonomous driving, current autonomous vehicles (AVs) lack effective bidirectional communication with occupants, limiting personalization and recovery from immobilization. This reduces comfort and trust, potentially slowing broader AV adoption. We propose PACE-ADS (Psychology and Cognition Enabled Automated Driving Systems), a human-centered autonomy framework that enables AVs to sense, interpret, and respond to both external traffic and internal occupant states. PACE-ADS comprises three foundation model-based agents: a Driver Agent that analyzes the driving context, a Psychologist Agent that interprets occupant psychological signals (e.g., EEG, heart rate, facial expressions) and cognitive commands (e.g., speech), and a Coordinator Agent that integrates these inputs to produce high-level behavior decisions and operational parameters. Rather than replacing existing AV modules, PACE-ADS complements them by operating at the behavioral level, delegating low-level control to native AV systems. This separation enables closed-loop adaptation and supports integration across diverse platforms. We evaluate PACE-ADS in simulation across varied scenarios involving traffic lights, pedestrians, work zones, and car following. Results show that PACE-ADS adapts driving styles to occupant states, improves ride comfort, and enables safe recovery from immobilization via autonomous reasoning or human guidance. Our findings highlight the promise of LLM-based frameworks for bridging the gap between machine autonomy and human-centered driving.
Large language models (LLMs) are increasingly used to simulate social behaviour, yet their political biases and interaction dynamics in debates remain underexplored. We investigate how LLM type and agent gender attributes influence political bias using a structured multi-agent debate framework, by engaging Neutral, Republican, and Democrat American LLM agents in debates on politically sensitive topics. We systematically vary the underlying LLMs, agent genders, and debate formats to examine how model provenance and agent personas influence political bias and attitudes throughout debates. We find that Neutral agents consistently align with Democrats, while Republicans shift closer to the Neutral; gender influences agent attitudes, with agents adapting their opinions when aware of other agents' genders; and contrary to prior research, agents with shared political affiliations can form echo chambers, exhibiting the expected intensification of attitudes as debates progress.
Rigorous security-focused evaluation of large language model (LLM) agents is imperative for establishing trust in their safe deployment throughout the software development lifecycle. However, existing benchmarks largely rely on synthetic challenges or simplified vulnerability datasets that fail to capture the complexity and ambiguity encountered by security engineers in practice. We introduce SEC-bench, the first fully automated benchmarking framework for evaluating LLM agents on authentic security engineering tasks. SEC-bench employs a novel multi-agent scaffold that automatically constructs code repositories with harnesses, reproduces vulnerabilities in isolated environments, and generates gold patches for reliable evaluation. Our framework automatically creates high-quality software vulnerability datasets with reproducible artifacts at a cost of only $0.87 per instance. Using SEC-bench, we implement two critical software security tasks to rigorously evaluate LLM agents' capabilities: proof-of-concept (PoC) generation and vulnerability patching. A comprehensive evaluation of state-of-the-art LLM code agents reveals significant performance gaps, achieving at most 18.0% success in PoC generation and 34.0% in vulnerability patching on our complete dataset. These results highlight the crucial steps needed toward developing LLM agents that are more practical, intelligent, and autonomous for security engineering.
A major obstacle in developing robust and generalizable smart home-based Human Activity Recognition (HAR) systems is the lack of large-scale, diverse labeled datasets. Variability in home layouts, sensor configurations, and user behavior adds further complexity, as individuals follow varied routines and perform activities in distinct ways. Building HAR systems that generalize well requires training data that captures the diversity across users and environments. To address these challenges, we introduce AgentSense, a virtual data generation pipeline where diverse personas are generated by leveraging Large Language Models. These personas are used to create daily routines, which are then decomposed into low-level action sequences. Subsequently, the actions are executed in a simulated home environment called VirtualHome that we extended with virtual ambient sensors capable of recording the agents activities as they unfold. Overall, AgentSense enables the generation of rich, virtual sensor datasets that represent a wide range of users and home settings. Across five benchmark HAR datasets, we show that leveraging our virtual sensor data substantially improves performance, particularly when real data are limited. Notably, models trained on a combination of virtual data and just a few days of real data achieve performance comparable to those trained on the entire real datasets. These results demonstrate and prove the potential of virtual data to address one of the most pressing challenges in ambient sensing, which is the distinct lack of large-scale, annotated datasets without requiring any manual data collection efforts.
Deep Research Agents are a prominent category of LLM-based agents. By autonomously orchestrating multistep web exploration, targeted retrieval, and higher-order synthesis, they transform vast amounts of online information into analyst-grade, citation-rich reports--compressing hours of manual desk research into minutes. However, a comprehensive benchmark for systematically evaluating the capabilities of these agents remains absent. To bridge this gap, we present DeepResearch Bench, a benchmark consisting of 100 PhD-level research tasks, each meticulously crafted by domain experts across 22 distinct fields. Evaluating DRAs is inherently complex and labor-intensive. We therefore propose two novel methodologies that achieve strong alignment with human judgment. The first is a reference-based method with adaptive criteria to assess the quality of generated research reports. The other framework is introduced to evaluate DRA's information retrieval and collection capabilities by assessing its effective citation count and overall citation accuracy. We have open-sourced DeepResearch Bench and key components of these frameworks at https://github.com/Ayanami0730/deep_research_bench to accelerate the development of practical LLM-based agents.
This paper addresses the challenge of transforming complex sentences into sequences of logical, simplified sentences while preserving semantic and logical integrity with the help of Large Language Models. We propose a hybrid approach that combines advanced prompting with multi-agent architectures to enhance the sentence simplification process. Experimental results show that our approach was able to successfully simplify 70% of the complex sentences written for video game design application. In comparison, a single-agent approach attained a 48% success rate on the same task.
Recent advances in reinforcement learning (RL) with verifiable outcome rewards have significantly improved the reasoning capabilities of large language models (LLMs), especially when combined with multi-turn tool interactions. However, existing methods lack both meaningful verification signals from realistic environments and explicit optimization for verification, leading to unreliable self-verification. To address these limitations, we propose ReVeal, a multi-turn reinforcement learning framework that interleaves code generation with explicit self-verification and tool-based evaluation. ReVeal enables LLMs to autonomously generate test cases, invoke external tools for precise feedback, and improves performance via a customized RL algorithm with dense, per-turn rewards. As a result, ReVeal fosters the co-evolution of a model's generation and verification capabilities through RL training, expanding the reasoning boundaries of the base model, demonstrated by significant gains in Pass@k on LiveCodeBench. It also enables test-time scaling into deeper inference regimes, with code consistently evolving as the number of turns increases during inference, ultimately surpassing DeepSeek-R1-Zero-Qwen-32B. These findings highlight the promise of ReVeal as a scalable and effective paradigm for building more robust and autonomous AI agents.
Reinforcement Learning from Verifiable Rewards (RLVR) has been widely adopted as the de facto method for enhancing the reasoning capabilities of large language models and has demonstrated notable success in verifiable domains like math and competitive programming tasks. However, the efficacy of RLVR diminishes significantly when applied to agentic environments. These settings, characterized by multi-step, complex problem solving, lead to high failure rates even for frontier LLMs, as the reward landscape is too sparse for effective model training via conventional RLVR. In this work, we introduce Agent-RLVR, a framework that makes RLVR effective in challenging agentic settings, with an initial focus on software engineering tasks. Inspired by human pedagogy, Agent-RLVR introduces agent guidance, a mechanism that actively steers the agent towards successful trajectories by leveraging diverse informational cues. These cues, ranging from high-level strategic plans to dynamic feedback on the agent's errors and environmental interactions, emulate a teacher's guidance, enabling the agent to navigate difficult solution spaces and promotes active self-improvement via additional environment exploration. In the Agent-RLVR training loop, agents first attempt to solve tasks to produce initial trajectories, which are then validated by unit tests and supplemented with agent guidance. Agents then reattempt with guidance, and the agent policy is updated with RLVR based on the rewards of these guided trajectories. Agent-RLVR elevates the pass@1 performance of Qwen-2.5-72B-Instruct from 9.4% to 22.4% on SWE-Bench Verified. We find that our guidance-augmented RLVR data is additionally useful for test-time reward model training, shown by further boosting pass@1 to 27.8%. Agent-RLVR lays the groundwork for training agents with RLVR in complex, real-world environments where conventional RL methods struggle.
Family caregivers often face substantial mental health challenges due to their multifaceted roles and limited resources. This study explored the potential of a large language model (LLM)-powered conversational agent to deliver evidence-based mental health support for caregivers, specifically Problem-Solving Therapy (PST) integrated with Motivational Interviewing (MI) and Behavioral Chain Analysis (BCA). A within-subject experiment was conducted with 28 caregivers interacting with four LLM configurations to evaluate empathy and therapeutic alliance. The best-performing models incorporated Few-Shot and Retrieval-Augmented Generation (RAG) prompting techniques, alongside clinician-curated examples. The models showed improved contextual understanding and personalized support, as reflected by qualitative responses and quantitative ratings on perceived empathy and therapeutic alliances. Participants valued the model's ability to validate emotions, explore unexpressed feelings, and provide actionable strategies. However, balancing thorough assessment with efficient advice delivery remains a challenge. This work highlights the potential of LLMs in delivering empathetic and tailored support for family caregivers.
The advent of large language models (LLMs) offers unprecedented opportunities to reimagine peer review beyond the constraints of traditional workflows. Despite these opportunities, prior efforts have largely focused on replicating traditional review workflows with LLMs serving as direct substitutes for human reviewers, while limited attention has been given to exploring new paradigms that fundamentally rethink how LLMs can participate in the academic review process. In this paper, we introduce and explore a novel mechanism that employs LLM agents to perform pairwise comparisons among manuscripts instead of individual scoring. By aggregating outcomes from substantial pairwise evaluations, this approach enables a more accurate and robust measure of relative manuscript quality. Our experiments demonstrate that this comparative approach significantly outperforms traditional rating-based methods in identifying high-impact papers. However, our analysis also reveals emergent biases in the selection process, notably a reduced novelty in research topics and an increased institutional imbalance. These findings highlight both the transformative potential of rethinking peer review with LLMs and critical challenges that future systems must address to ensure equity and diversity.
World models aim to simulate environments and enable effective agent behavior. However, modeling real-world environments presents unique challenges as they dynamically change across both space and, crucially, time. To capture these composed dynamics, we introduce a Spatio-Temporal Road Image Dataset for Exploration (STRIDE) permuting 360-degree panoramic imagery into rich interconnected observation, state and action nodes. Leveraging this structure, we can simultaneously model the relationship between egocentric views, positional coordinates, and movement commands across both space and time. We benchmark this dataset via TARDIS, a transformer-based generative world model that integrates spatial and temporal dynamics through a unified autoregressive framework trained on STRIDE. We demonstrate robust performance across a range of agentic tasks such as controllable photorealistic image synthesis, instruction following, autonomous self-control, and state-of-the-art georeferencing. These results suggest a promising direction towards sophisticated generalist agents--capable of understanding and manipulating the spatial and temporal aspects of their material environments--with enhanced embodied reasoning capabilities. Training code, datasets, and model checkpoints are made available at https://huggingface.co/datasets/Tera-AI/STRIDE.
Large language models (LLMs) are routinely deployed as agentic systems, with access to tools that interact with live environments to accomplish tasks. In enterprise deployments these systems need to interact with API collections that can be extremely large and complex, often backed by databases. In order to create datasets with such characteristics, we explore how existing NL2SQL (Natural Language to SQL query) datasets can be used to automatically create NL2API datasets. Specifically, this work describes a novel data generation pipeline that exploits the syntax of SQL queries to construct a functionally equivalent sequence of API calls. We apply this pipeline to one of the largest NL2SQL datasets, BIRD-SQL to create a collection of over 2500 APIs that can be served as invocable tools or REST-endpoints. We pair natural language queries from BIRD-SQL to ground-truth API sequences based on this API pool. We use this collection to study the performance of 10 public LLMs and find that all models struggle to determine the right set of tools (consisting of tasks of intent detection, sequencing with nested function calls, and slot-filling). We find that models have extremely low task completion rates (7-47 percent - depending on the dataset) which marginally improves to 50 percent when models are employed as ReACT agents that interact with the live API environment. The best task completion rates are far below what may be required for effective general-use tool-calling agents, suggesting substantial scope for improvement in current state-of-the-art tool-calling LLMs. We also conduct detailed ablation studies, such as assessing the impact of the number of tools available as well as the impact of tool and slot-name obfuscation. We compare the performance of models on the original SQL generation tasks and find that current models are sometimes able to exploit SQL better than APIs.
In an effort to automatically evaluate and select the best model and improve code quality for automatic incident remediation in IT Automation, it is crucial to verify if the generated code for remediation action is syntactically and semantically correct and whether it can be executed correctly as intended. There are three approaches: 1) conventional methods use surface form similarity metrics (token match, exact match, etc.) which have numerous limitations, 2) execution-based evaluation focuses more on code functionality based on pass/fail judgments for given test-cases, and 3) LLM-as-a-Judge employs LLMs for automated evaluation to judge if it is a correct answer for a given problem based on pre-defined metrics. In this work, we focused on enhancing LLM-as-a-Judge using bidirectional functionality matching and logic representation for reference-less automatic validation and refinement for Bash code generation to select the best model for automatic incident remediation in IT Automation. We used execution-based evaluation as ground-truth to evaluate our LLM-as-a-Judge metrics. Results show high accuracy and agreement with execution-based evaluation (and up to 8% over baseline). Finally, we built Reflection code agents to utilize judgments and feedback from our evaluation metrics which achieved significant improvement (up to 24% increase in accuracy) for automatic code refinement.
Large Language Model (LLM) agents have shown great potential in addressing real-world data science problems. LLM-driven data science agents promise to automate the entire machine learning pipeline, yet their real-world effectiveness remains limited. Existing frameworks depend on rigid, pre-defined workflows and inflexible coding strategies; consequently, they excel only on relatively simple, classical problems and fail to capture the empirical expertise that human practitioners bring to complex, innovative tasks. In this work, we introduce AutoMind, an adaptive, knowledgeable LLM-agent framework that overcomes these deficiencies through three key advances: (1) a curated expert knowledge base that grounds the agent in domain expert knowledge, (2) an agentic knowledgeable tree search algorithm that strategically explores possible solutions, and (3) a self-adaptive coding strategy that dynamically tailors code generation to task complexity. Evaluations on two automated data science benchmarks demonstrate that AutoMind delivers superior performance versus state-of-the-art baselines. Additional analyses confirm favorable effectiveness, efficiency, and qualitative solution quality, highlighting AutoMind as an efficient and robust step toward fully automated data science.
Constructing large-scale datasets for the GitHub issue resolution task is crucial for both training and evaluating the software engineering capabilities of Large Language Models (LLMs). However, the traditional process for creating such benchmarks is notoriously challenging and labor-intensive, particularly in the stages of setting up evaluation environments, grading test outcomes, and validating task instances. In this paper, we propose SWE-Factory, an automated pipeline designed to address these challenges. To tackle these issues, our pipeline integrates three core automated components. First, we introduce SWE-Builder, a multi-agent system that automates evaluation environment construction, which employs four specialized agents that work in a collaborative, iterative loop and leverages an environment memory pool to enhance efficiency. Second, we introduce a standardized, exit-code-based grading method that eliminates the need for manually writing custom parsers. Finally, we automate the fail2pass validation process using these reliable exit code signals. Experiments on 671 issues across four programming languages show that our pipeline can effectively construct valid task instances; for example, with GPT-4.1-mini, our SWE-Builder constructs 269 valid instances at $0.045 per instance, while with Gemini-2.5-flash, it achieves comparable performance at the lowest cost of $0.024 per instance. We also demonstrate that our exit-code-based grading achieves 100% accuracy compared to manual inspection, and our automated fail2pass validation reaches a precision of 0.92 and a recall of 1.00. We hope our automated pipeline will accelerate the collection of large-scale, high-quality GitHub issue resolution datasets for both training and evaluation. Our code and datasets are released at https://github.com/DeepSoftwareAnalytics/swe-factory.
Recent advancements in Large Language Models (LLMs) and multimodal counterparts have spurred significant interest in developing web agents -- AI systems capable of autonomously navigating and completing tasks within web environments. While holding tremendous promise for automating complex web interactions, current approaches face substantial challenges due to the fundamental mismatch between human-designed interfaces and LLM capabilities. Current methods struggle with the inherent complexity of web inputs, whether processing massive DOM trees, relying on screenshots augmented with additional information, or bypassing the user interface entirely through API interactions. This position paper advocates for a paradigm shift in web agent research: rather than forcing web agents to adapt to interfaces designed for humans, we should develop a new interaction paradigm specifically optimized for agentic capabilities. To this end, we introduce the concept of an Agentic Web Interface (AWI), an interface specifically designed for agents to navigate a website. We establish six guiding principles for AWI design, emphasizing safety, efficiency, and standardization, to account for the interests of all primary stakeholders. This reframing aims to overcome fundamental limitations of existing interfaces, paving the way for more efficient, reliable, and transparent web agent design, which will be a collaborative effort involving the broader ML community.
Current LLM safety defenses fail under decomposition attacks, where a malicious goal is decomposed into benign subtasks that circumvent refusals. The challenge lies in the existing shallow safety alignment techniques: they only detect harm in the immediate prompt and do not reason about long-range intent, leaving them blind to malicious intent that emerges over a sequence of seemingly benign instructions. We therefore propose adding an external monitor that observes the conversation at a higher granularity. To facilitate our study of monitoring decomposition attacks, we curate the largest and most diverse dataset to date, including question-answering, text-to-image, and agentic tasks. We verify our datasets by testing them on frontier LLMs and show an 87% attack success rate on average on GPT-4o. This confirms that decomposition attack is broadly effective. Additionally, we find that random tasks can be injected into the decomposed subtasks to further obfuscate malicious intents. To defend in real time, we propose a lightweight sequential monitoring framework that cumulatively evaluates each subtask. We show that a carefully prompt engineered lightweight monitor achieves a 93% defense success rate, beating reasoning models like o3 mini as a monitor. Moreover, it remains robust against random task injection and cuts cost by 90% and latency by 50%. Our findings suggest that lightweight sequential monitors are highly effective in mitigating decomposition attacks and are viable in deployment.
We present a novel approach to neural code generation that incorporates real-time execution signals into the language model generation process. While large language models (LLMs) have demonstrated impressive code generation capabilities, they typically do not utilize execution feedback during inference, a critical signal that human programmers regularly leverage. Our method, Execution-Guided Classifier-Free Guidance (EG-CFG), dynamically incorporates execution signals as the model generates code, providing line-by-line feedback that guides the generation process toward executable solutions. EG-CFG employs a multi-stage process: first, we conduct beam search to sample candidate program completions for each line; second, we extract execution signals by executing these candidates against test cases; and finally, we incorporate these signals into the prompt during generation. By maintaining consistent signals across tokens within the same line and refreshing signals at line boundaries, our approach provides coherent guidance while preserving syntactic structure. Moreover, the method naturally supports native parallelism at the task level in which multiple agents operate in parallel, exploring diverse reasoning paths and collectively generating a broad set of candidate solutions. Our experiments across diverse coding tasks demonstrate that EG-CFG significantly improves code generation performance compared to standard approaches, achieving state-of-the-art results across various levels of complexity, from foundational problems to challenging competitive programming tasks. Our code is available at: https://github.com/boazlavon/eg_cfg
Recent developments in aligning Large Language Models (LLMs) with human preferences have significantly enhanced their utility in human-AI collaborative scenarios. However, such approaches often neglect the critical role of "epistemic friction," or the inherent resistance encountered when updating beliefs in response to new, conflicting, or ambiguous information. In this paper, we define dynamic epistemic friction as the resistance to epistemic integration, characterized by the misalignment between an agent's current belief state and new propositions supported by external evidence. We position this within the framework of Dynamic Epistemic Logic (Van Benthem and Pacuit, 2011), where friction emerges as nontrivial belief-revision during the interaction. We then present analyses from a situated collaborative task that demonstrate how this model of epistemic friction can effectively predict belief updates in dialogues, and we subsequently discuss how the model of belief alignment as a measure of epistemic resistance or friction can naturally be made more sophisticated to accommodate the complexities of real-world dialogue scenarios.
Large Language Models (LLMs) have shown remarkable capabilities in solving diverse tasks. However, their proficiency in iteratively optimizing complex solutions through learning from previous feedback remains insufficiently explored. To bridge this gap, we present OPT-BENCH, a comprehensive benchmark designed to evaluate LLM agents on large-scale search space optimization problems. OPT-BENCH includes 20 real-world machine learning tasks sourced from Kaggle and 10 classical NP problems, offering a diverse and challenging environment for assessing LLM agents on iterative reasoning and solution refinement. To enable rigorous evaluation, we introduce OPT-Agent, an end-to-end optimization framework that emulates human reasoning when tackling complex problems by generating, validating, and iteratively improving solutions through leveraging historical feedback. Through extensive experiments on 9 state-of-the-art LLMs from 6 model families, we analyze the effects of optimization iterations, temperature settings, and model architectures on solution quality and convergence. Our results demonstrate that incorporating historical context significantly enhances optimization performance across both ML and NP tasks. All datasets, code, and evaluation tools are open-sourced to promote further research in advancing LLM-driven optimization and iterative reasoning. Project page: \href{https://github.com/OliverLeeXZ/OPT-BENCH}{https://github.com/OliverLeeXZ/OPT-BENCH}.
Text animation, a foundational element in video creation, enables efficient and cost-effective communication, thriving in advertisements, journalism, and social media. However, traditional animation workflows present significant usability barriers for non-professionals, with intricate operational procedures severely hindering creative productivity. To address this, we propose a Large Language Model (LLM)-aided text animation editing system that enables real-time intent tracking and flexible editing. The system introduces an agent-based dual-stream pipeline that integrates context-aware inline suggestions and conversational guidance as well as employs a semantic-animation mapping to facilitate LLM-driven creative intent translation. Besides, the system supports synchronized text-animation previews and parametric adjustments via unified controls to improve editing workflow. A user study evaluates the system, highlighting its ability to help non-professional users complete animation workflows while validating the pipeline. The findings encourage further exploration of integrating LLMs into a comprehensive video creation workflow.
Vision-and-language navigation (VLN) is a long-standing challenge in autonomous robotics, aiming to empower agents with the ability to follow human instructions while navigating complex environments. Two key bottlenecks remain in this field: generalization to out-of-distribution environments and reliance on fixed discrete action spaces. To address these challenges, we propose Vision-Language Fly (VLFly), a framework tailored for Unmanned Aerial Vehicles (UAVs) to execute language-guided flight. Without the requirement for localization or active ranging sensors, VLFly outputs continuous velocity commands purely from egocentric observations captured by an onboard monocular camera. The VLFly integrates three modules: an instruction encoder based on a large language model (LLM) that reformulates high-level language into structured prompts, a goal retriever powered by a vision-language model (VLM) that matches these prompts to goal images via vision-language similarity, and a waypoint planner that generates executable trajectories for real-time UAV control. VLFly is evaluated across diverse simulation environments without additional fine-tuning and consistently outperforms all baselines. Moreover, real-world VLN tasks in indoor and outdoor environments under direct and indirect instructions demonstrate that VLFly achieves robust open-vocabulary goal understanding and generalized navigation capabilities, even in the presence of abstract language input.
Explicit modeling of capabilities and skills -- whether based on ontologies, Asset Administration Shells, or other technologies -- requires considerable manual effort and often results in representations that are not easily accessible to Large Language Models (LLMs). In this work-in-progress paper, we present an alternative approach based on the recently introduced Model Context Protocol (MCP). MCP allows systems to expose functionality through a standardized interface that is directly consumable by LLM-based agents. We conduct a prototypical evaluation on a laboratory-scale manufacturing system, where resource functions are made available via MCP. A general-purpose LLM is then tasked with planning and executing a multi-step process, including constraint handling and the invocation of resource functions via MCP. The results indicate that such an approach can enable flexible industrial automation without relying on explicit semantic models. This work lays the basis for further exploration of external tool integration in LLM-driven production systems.
The advancement of conversational AI systems relies on the availability of high-quality, flexible, and reproducible synthetic dialogues for training, evaluation, and benchmarking. SDialog is a modular, extensible Python toolkit designed to address the challenges of synthetic dialogue generation and analysis. By leveraging instruction-tuned Large Language Models (LLMs), SDialog provides abstractions for personas, orchestration, and scenario management, enabling the creation of realistic, diverse, and controllable conversational data for research and development. SDialog supports workflows such as multi-agent simulation and scenario-driven generation, and represents a step forward in the standardization of tools and frameworks for synthetic data generation, a crucial advancement for ensuring reproducibility in today's fast-evolving research landscape.
Large language models (LLMs) have demonstrated remarkable performance in zero-shot dialogue state tracking (DST), reducing the need for task-specific training. However, conventional DST benchmarks primarily focus on structured user-agent conversations, failing to capture the complexities of real-world multi-user interactions. In this study, we assess the robustness of LLMs in multi-user DST while minimizing dataset construction costs. Inspired by recent advances in LLM-based data annotation, we extend an existing DST dataset by generating utterances of a second user based on speech act theory. Our methodology systematically incorporates a second user's utterances into conversations, enabling a controlled evaluation of LLMs in multi-user settings. Experimental results reveal a significant performance drop compared to single-user DST, highlighting the limitations of current LLMs in extracting and tracking dialogue states amidst multiple speakers. Our findings emphasize the need for future research to enhance LLMs for multi-user DST scenarios, paving the way for more realistic and robust DST models.
Hardware complexity continues to strain verification resources, motivating the adoption of machine learning (ML) methods to improve debug efficiency. However, ML-assisted debugging critically depends on diverse and scalable bug datasets, which existing manual or automated bug insertion methods fail to reliably produce. We introduce BugGen, a first of its kind, fully autonomous, multi-agent pipeline leveraging Large Language Models (LLMs) to systematically generate, insert, and validate realistic functional bugs in RTL. BugGen partitions modules, selects mutation targets via a closed-loop agentic architecture, and employs iterative refinement and rollback mechanisms to ensure syntactic correctness and functional detectability. Evaluated across five OpenTitan IP blocks, BugGen produced 500 unique bugs with 94% functional accuracy and achieved a throughput of 17.7 validated bugs per hour-over five times faster than typical manual expert insertion. Additionally, BugGen identified 104 previously undetected bugs in OpenTitan regressions, highlighting its utility in exposing verification coverage gaps. Compared against Certitude, BugGen demonstrated over twice the syntactic accuracy, deeper exposure of testbench blind spots, and more functionally meaningful and complex bug scenarios. Furthermore, when these BugGen-generated datasets were employed to train ML-based failure triage models, we achieved high classification accuracy (88.1%-93.2%) across different IP blocks, confirming the practical utility and realism of generated bugs. BugGen thus provides a scalable solution for generating high-quality bug datasets, significantly enhancing verification efficiency and ML-assisted debugging.
Recent advancements in LLMs indicate potential for novel applications, e.g., through reasoning capabilities in the latest OpenAI and DeepSeek models. For applying these models in specific domains beyond text generation, LLM-based multi-agent approaches can be utilized that solve complex tasks by combining reasoning techniques, code generation, and software execution. Applications might utilize these capabilities and the knowledge of specialized LLM agents. However, while many evaluations are performed on LLMs, reasoning techniques, and applications individually, their joint specification and combined application is not explored well. Defined specifications for multi-agent LLM systems are required to explore their potential and their suitability for specific applications, allowing for systematic evaluations of LLMs, reasoning techniques, and related aspects. This paper reports the results of exploratory research to specify and evaluate these aspects through a multi-agent system. The system architecture and prototype are extended from previous research and a specification is introduced for multi-agent systems. Test cases involving cybersecurity tasks indicate feasibility of the architecture and evaluation approach. In particular, the results show the evaluation of question answering, server security, and network security tasks that were completed correctly by agents with LLMs from OpenAI and DeepSeek.
Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to overcome the knowledge limitations of Large Language Models (LLMs) by integrating external retrieval with language generation. While early RAG systems based on static pipelines have shown effectiveness in well-structured tasks, they struggle in real-world scenarios requiring complex reasoning, dynamic retrieval, and multi-modal integration. To address these challenges, the field has shifted toward Reasoning Agentic RAG, a paradigm that embeds decision-making and adaptive tool use directly into the retrieval process. In this paper, we present a comprehensive review of Reasoning Agentic RAG methods, categorizing them into two primary systems: predefined reasoning, which follows fixed modular pipelines to boost reasoning, and agentic reasoning, where the model autonomously orchestrates tool interaction during inference. We analyze representative techniques under both paradigms, covering architectural design, reasoning strategies, and tool coordination. Finally, we discuss key research challenges and propose future directions to advance the flexibility, robustness, and applicability of reasoning agentic RAG systems. Our collection of the relevant research has been organized into a https://github.com/ByebyeMonica/Reasoning-Agentic-RAG.
Interactively learning from observation and language feedback is an increasingly studied area driven by the emergence of large language model (LLM) agents. While impressive empirical demonstrations have been shown, so far a principled framing of these decision problems remains lacking. In this paper, we formalize the Learning from Language Feedback (LLF) problem, assert sufficient assumptions to enable learning despite latent rewards, and introduce $\textit{transfer eluder dimension}$ as a complexity measure to characterize the hardness of LLF problems. We show that transfer eluder dimension captures the intuition that information in the feedback changes the learning complexity of the LLF problem. We demonstrate cases where learning from rich language feedback can be exponentially faster than learning from reward. We develop a no-regret algorithm, called $\texttt{HELiX}$, that provably solves LLF problems through sequential interactions, with performance guarantees that scale with the transfer eluder dimension of the problem. Across several empirical domains, we show that $\texttt{HELiX}$ performs well even when repeatedly prompting LLMs does not work reliably. Our contributions mark a first step towards designing principled interactive learning algorithms from generic language feedback.
Static bug analyzers play a crucial role in ensuring software quality. However, existing analyzers for bug detection in large codebases often suffer from high false positive rates. This is primarily due to the limited capabilities of analyzers in path feasibility validation with multiple conditional branches and complex data dependencies. While current LLM-based approaches attempt to address this issue, their effectiveness remains limited due to insufficient constraint cascade analysis and scalability challenges in large projects. To address this challenge, we propose an iterative path feasibility analysis framework LLM4PFA. By leveraging LLM agent based targeted constraint reasoning, and key context-aware analysis driven by agent planning, LLM4PFA effectively enhances complex inter-procedural path feasibility analysis for minimizing false positives in static bug detection. Evaluation results show that LLM4PFA precisely filters out 72% to 96% false positives reported during static bug detection, significantly outperforming all the baselines by 41.1% - 105.7% improvements; meanwhile LLM4PFA only misses 3 real bugs of 45 true positives.