We propose CURE, a novel reinforcement learning framework with a dedicated reward design that co-evolves coding and unit test generation capabilities based on their interaction outcomes, without any ground-truth code as supervision. This approach enables flexible and scalable training and allows the unit tester to learn directly from the coder's mistakes. Our derived ReasonFlux-Coder-7B and 14B models improve code generation accuracy by 5.3% and Best-of-N accuracy by 9.0% after optimization on Qwen2.5-Instruct models, outperforming similarly sized Qwen-Coder, DeepSeek-Coder, and Seed-Coder. They naturally extend to downstream tasks such as test-time scaling and agentic coding-achieving a 8.1% improvement over the base model. For the long-CoT model, our ReasonFlux-Coder-4B consistently outperforms Qwen3-4B while achieving 64.8% inference efficiency in unit test generation. Notably, we also find that our model can serve as an effective reward model for reinforcement learning on base models. Project: https://github.com/Gen-Verse/CURE
Computer use agents (CUA) are systems that automatically interact with graphical user interfaces (GUIs) to complete tasks. CUA have made significant progress with the advent of large vision-language models (VLMs). However, these agents typically rely on cloud-based inference with substantial compute demands, raising critical privacy and scalability concerns, especially when operating on personal devices. In this work, we take a step toward privacy-preserving and resource-efficient agents by developing a lightweight vision-language model that runs entirely on local machines. To train this compact agent, we introduce an LLM-as-Judge framework that automatically evaluates and filters synthetic interaction trajectories, producing high-quality data for reinforcement learning without human annotation. Experiments on the OS-World benchmark demonstrate that our fine-tuned local model outperforms existing baselines, highlighting a promising path toward private, efficient, and generalizable GUI agents.
Traditional AI safety evaluations on isolated LLMs are insufficient as multi-agent AI ensembles become prevalent, introducing novel emergent risks. This paper introduces the Multi-Agent Emergent Behavior Evaluation (MAEBE) framework to systematically assess such risks. Using MAEBE with the Greatest Good Benchmark (and a novel double-inversion question technique), we demonstrate that: (1) LLM moral preferences, particularly for Instrumental Harm, are surprisingly brittle and shift significantly with question framing, both in single agents and ensembles. (2) The moral reasoning of LLM ensembles is not directly predictable from isolated agent behavior due to emergent group dynamics. (3) Specifically, ensembles exhibit phenomena like peer pressure influencing convergence, even when guided by a supervisor, highlighting distinct safety and alignment challenges. Our findings underscore the necessity of evaluating AI systems in their interactive, multi-agent contexts.
Reinforcement learning (RL) enhances large language models (LLMs) in complex, long-chain-of-thought (long-CoT) reasoning. The advanced VAPO framework, despite sophisticated mechanisms like Decoupled GAE, theoretically faces fundamental limitations in comprehensively modeling and leveraging deep, long-term value for fine-grained, step-by-step policy guidance in extended reasoning chains. We argue these limitations stem from inherent difficulties in credit assignment, value function representational capacity with temporally abstracted goals, and translating global value signals into local policy improvements, especially with sparse rewards. Our theoretical analysis examines these aspects to illuminate VAPO's boundaries in long-term value modeling, aiming to deepen understanding of current RL for advanced reasoning and suggest future research for more robust LLM agents.
Accurately assessing internal human states is key to understanding preferences, offering personalized services, and identifying challenges in real-world applications. Originating from psychometrics, adaptive testing has become the mainstream method for human measurement and has now been widely applied in education, healthcare, sports, and sociology. It customizes assessments by selecting the fewest test questions . However, current adaptive testing methods face several challenges. The mechanized nature of most algorithms leads to guessing behavior and difficulties with open-ended questions. Additionally, subjective assessments suffer from noisy response data and coarse-grained test outputs, further limiting their effectiveness. To move closer to an ideal adaptive testing process, we propose TestAgent, a large language model (LLM)-powered agent designed to enhance adaptive testing through interactive engagement. This is the first application of LLMs in adaptive testing. TestAgent supports personalized question selection, captures test-takers' responses and anomalies, and provides precise outcomes through dynamic, conversational interactions. Experiments on psychological, educational, and lifestyle assessments show our approach achieves more accurate results with 20% fewer questions than state-of-the-art baselines, and testers preferred it in speed, smoothness, and other dimensions.
Large Language Models (LLMs) are increasingly explored for legal argument generation, yet they pose significant risks of manipulation through hallucination and ungrounded persuasion, and often fail to utilize provided factual bases effectively or abstain when arguments are untenable. This paper introduces a novel reflective multi-agent method designed to address these challenges in the context of legally compliant persuasion. Our approach employs specialized agents--a Factor Analyst and an Argument Polisher--in an iterative refinement process to generate 3-ply legal arguments (plaintiff, defendant, rebuttal). We evaluate Reflective Multi-Agent against single-agent, enhanced-prompt single-agent, and non-reflective multi-agent baselines using four diverse LLMs (GPT-4o, GPT-4o-mini, Llama-4-Maverick-17b-128e, Llama-4-Scout-17b-16e) across three legal scenarios: "arguable", "mismatched", and "non-arguable". Results demonstrate Reflective Multi-Agent's significant superiority in successful abstention (preventing generation when arguments cannot be grounded), marked improvements in hallucination accuracy (reducing fabricated and misattributed factors), particularly in "non-arguable" scenarios, and enhanced factor utilization recall (improving the use of provided case facts). These findings suggest that structured reflection within a multi-agent framework offers a robust computable method for fostering ethical persuasion and mitigating manipulation in LLM-based legal argumentation systems, a critical step towards trustworthy AI in law. Project page: https://lizhang-aiandlaw.github.io/A-Reflective-Multi-Agent-Approach-for-Legal-Argument-Generation/
Large Language Model (LLM) based multi-agent systems have shown remarkable performance in various tasks, especially when enhanced through collaborative communication. However, current methods often rely on a fixed number of agents and static communication structures, limiting their ability to adapt to varying task complexities. In this paper, we propose Adaptive Graph Pruning (AGP), a novel task-adaptive multi-agent collaboration framework that jointly optimizes agent quantity (hard-pruning) and communication topology (soft-pruning). Specifically, our method employs a two-stage training strategy: firstly, independently training soft-pruning networks for different agent quantities to determine optimal agent-quantity-specific complete graphs and positional masks across specific tasks; and then jointly optimizing hard-pruning and soft-pruning within a maximum complete graph to dynamically configure the number of agents and their communication topologies per task. Extensive experiments demonstrate that our approach is: (1) High-performing, achieving state-of-the-art results across six benchmarks and consistently generalizes across multiple mainstream LLM architectures, with a increase in performance of $2.58\%\sim 9.84\%$; (2) Task-adaptive, dynamically constructing optimized communication topologies tailored to specific tasks, with an extremely high performance in all three task categories (general reasoning, mathematical reasoning, and code generation); (3) Token-economical, having fewer training steps and token consumption at the same time, with a decrease in token consumption of $90\%+$; and (4) Training-efficient, achieving high performance with very few training steps compared with other methods. The performance will surpass the existing baselines after about ten steps of training under six benchmarks.
Unit testing plays a critical role in ensuring software correctness. However, writing unit tests manually is laborious, especially for strong typed languages like Java, motivating the need for automated approaches. Traditional methods primarily rely on search-based or randomized algorithms to generate tests that achieve high code coverage and produce regression oracles, which are derived from the program's current behavior rather than its intended functionality. Recent advances in large language models (LLMs) have enabled oracle generation from natural language descriptions. However, existing LLM-based methods often require LLM fine-tuning or rely on external tools such as EvoSuite for test prefix generation. In this work, we propose CANDOR, a novel end-to-end, prompt-based LLM framework for automated JUnit test generation. CANDOR orchestrates multiple specialized LLM agents to generate JUnit tests, including both high-quality test prefixes and accurate oracles. To mitigate the notorious hallucinations in LLMs, we introduce a novel strategy that engages multiple reasoning LLMs in a panel discussion and generate accurate oracles based on consensus. Additionally, to reduce the verbosity of reasoning LLMs' outputs, we propose a novel dual-LLM pipeline to produce concise and structured oracle evaluations. Our experiments on the HumanEvalJava and LeetCodeJava datasets show that CANDOR can generate accurate oracles and is slightly better than EvoSuite in generating tests with high line coverage and clearly superior in terms of mutation score. Moreover, CANDOR significantly outperforms the state-of-the-art, prompt-based test generator LLM-Empirical, achieving improvements of 15.8 to 25.1 percentage points in oracle correctness on both correct and faulty source code. Ablation studies confirm the critical contributions of key agents in improving test prefix quality and oracle accuracy.
Computer System Architecture serves as a crucial bridge between software applications and the underlying hardware, encompassing components like compilers, CPUs, coprocessors, and RTL designs. Its development, from early mainframes to modern domain-specific architectures, has been driven by rising computational demands and advancements in semiconductor technology. However, traditional paradigms in computer system architecture design are confronting significant challenges, including a reliance on manual expertise, fragmented optimization across software and hardware layers, and high costs associated with exploring expansive design spaces. While automated methods leveraging optimization algorithms and machine learning have improved efficiency, they remain constrained by a single-stage focus, limited data availability, and a lack of comprehensive human domain knowledge. The emergence of large language models offers transformative opportunities for the design of computer system architecture. By leveraging the capabilities of LLMs in areas such as code generation, data analysis, and performance modeling, the traditional manual design process can be transitioned to a machine-based automated design approach. To harness this potential, we present the Large Processor Chip Model (LPCM), an LLM-driven framework aimed at achieving end-to-end automated computer architecture design. The LPCM is structured into three levels: Human-Centric; Agent-Orchestrated; and Model-Governed. This paper utilizes 3D Gaussian Splatting as a representative workload and employs the concept of software-hardware collaborative design to examine the implementation of the LPCM at Level 1, demonstrating the effectiveness of the proposed approach. Furthermore, this paper provides an in-depth discussion on the pathway to implementing Level 2 and Level 3 of the LPCM, along with an analysis of the existing challenges.
Persuasion is a powerful capability of large language models (LLMs) that both enables beneficial applications (e.g. helping people quit smoking) and raises significant risks (e.g. large-scale, targeted political manipulation). Prior work has found models possess a significant and growing persuasive capability, measured by belief changes in simulated or real users. However, these benchmarks overlook a crucial risk factor: the propensity of a model to attempt to persuade in harmful contexts. Understanding whether a model will blindly ``follow orders'' to persuade on harmful topics (e.g. glorifying joining a terrorist group) is key to understanding the efficacy of safety guardrails. Moreover, understanding if and when a model will engage in persuasive behavior in pursuit of some goal is essential to understanding the risks from agentic AI systems. We propose the Attempt to Persuade Eval (APE) benchmark, that shifts the focus from persuasion success to persuasion attempts, operationalized as a model's willingness to generate content aimed at shaping beliefs or behavior. Our evaluation framework probes frontier LLMs using a multi-turn conversational setup between simulated persuader and persuadee agents. APE explores a diverse spectrum of topics including conspiracies, controversial issues, and non-controversially harmful content. We introduce an automated evaluator model to identify willingness to persuade and measure the frequency and context of persuasive attempts. We find that many open and closed-weight models are frequently willing to attempt persuasion on harmful topics and that jailbreaking can increase willingness to engage in such behavior. Our results highlight gaps in current safety guardrails and underscore the importance of evaluating willingness to persuade as a key dimension of LLM risk. APE is available at github.com/AlignmentResearch/AttemptPersuadeEval
Evaluating the security of multi-agent systems (MASs) powered by large language models (LLMs) is challenging, primarily because of the systems' complex internal dynamics and the evolving nature of LLM vulnerabilities. Traditional attack graph (AG) methods often lack the specific capabilities to model attacks on LLMs. This paper introduces AI-agent application Threat assessment with Attack Graphs (ATAG), a novel framework designed to systematically analyze the security risks associated with AI-agent applications. ATAG extends the MulVAL logic-based AG generation tool with custom facts and interaction rules to accurately represent AI-agent topologies, vulnerabilities, and attack scenarios. As part of this research, we also created the LLM vulnerability database (LVD) to initiate the process of standardizing LLM vulnerabilities documentation. To demonstrate ATAG's efficacy, we applied it to two multi-agent applications. Our case studies demonstrated the framework's ability to model and generate AGs for sophisticated, multi-step attack scenarios exploiting vulnerabilities such as prompt injection, excessive agency, sensitive information disclosure, and insecure output handling across interconnected agents. ATAG is an important step toward a robust methodology and toolset to help understand, visualize, and prioritize complex attack paths in multi-agent AI systems (MAASs). It facilitates proactive identification and mitigation of AI-agent threats in multi-agent applications.
Economic inequality is a global challenge, intensifying disparities in education, healthcare, and social stability. Traditional systems like the U.S. federal income tax reduce inequality but lack adaptability. Although models like the Saez Optimal Taxation adjust dynamically, they fail to address taxpayer heterogeneity and irrational behavior. This study introduces TaxAgent, a novel integration of large language models (LLMs) with agent-based modeling (ABM) to design adaptive tax policies. In our macroeconomic simulation, heterogeneous H-Agents (households) simulate real-world taxpayer behaviors while the TaxAgent (government) utilizes LLMs to iteratively optimize tax rates, balancing equity and productivity. Benchmarked against Saez Optimal Taxation, U.S. federal income taxes, and free markets, TaxAgent achieves superior equity-efficiency trade-offs. This research offers a novel taxation solution and a scalable, data-driven framework for fiscal policy evaluation.
Large Language Models (LLMs) have become foundational to modern AI agent systems, enabling autonomous agents to reason and plan. In most existing systems, inter-agent communication relies primarily on natural language. While this design supports interpretability and human oversight, we argue that it introduces fundamental limitations in agent-to-agent coordination. The semantic space of natural language is structurally misaligned with the high-dimensional vector spaces in which LLMs operate, resulting in information loss and behavioral drift. Beyond surface-level inefficiencies, we highlight a deeper architectural limitation: current LLMs were not trained with the objective of supporting agentic behavior. As such, they lack mechanisms for modeling role continuity, task boundaries, and multi-agent dependencies. The standard next-token prediction paradigm fails to support the structural alignment required for robust, scalable agent coordination. Based on this, we argue that two core questions deserve careful examination: first, given that AI agents fundamentally operate in high-dimensional vector spaces, should they rely on a language system originally designed for human cognition as their communication medium? Second, should we consider developing a new model construction paradigm that builds models from the ground up to natively support structured communication, shared intentionality, and task alignment in multi-role, multi-agent environments? This paper calls for a reconsideration not only of how agents should communicate, but also of what it fundamentally means to train a model that natively supports multi-agent coordination and communication.
Large language models (LLMs) have exhibited remarkable capabilities and achieved significant breakthroughs across various domains, leading to their widespread adoption in recent years. Building on this progress, we investigate their potential in the realm of local life services. In this study, we establish a comprehensive benchmark and systematically evaluate the performance of diverse LLMs across a wide range of tasks relevant to local life services. To further enhance their effectiveness, we explore two key approaches: model fine-tuning and agent-based workflows. Our findings reveal that even a relatively compact 7B model can attain performance levels comparable to a much larger 72B model, effectively balancing inference cost and model capability. This optimization greatly enhances the feasibility and efficiency of deploying LLMs in real-world online services, making them more practical and accessible for local life applications.
Large Language Models (LLMs) have achieved remarkable success across diverse natural language processing tasks, yet their deployment in real-world applications is hindered by fixed knowledge cutoffs and difficulties in generating controllable, accurate outputs in a single inference. Multi-agent systems (MAS) built from specialized LLM agents offer a promising solution, enabling dynamic collaboration and iterative reasoning. However, optimizing these systems remains a challenge, as conventional methods such as prompt engineering and supervised fine-tuning entail high engineering overhead and limited adaptability. Reinforcement learning (RL), particularly multi-agent reinforcement learning (MARL), provides a scalable framework by refining agent policies based on system-level feedback. Nevertheless, existing MARL algorithms, such as Multi-Agent Proximal Policy Optimization (MAPPO), rely on Critic networks, which can cause training instability and increase computational burden. To address these limitations and target the prototypical Multi-Agent Search System (MASS), we propose Multi-Agent Heterogeneous Group Policy Optimization (MHGPO), a novel Critic-free algorithm that guides policy updates by estimating relative reward advantages across heterogeneous groups of rollouts. MHGPO eliminates the need for Critic networks, enhancing stability and reducing computational overhead. Additionally, we introduce three group rollout sampling strategies that trade off between efficiency and effectiveness. Experiments on a multi-agent LLM-based search system demonstrate that MHGPO consistently outperforms MAPPO in both task performance and computational efficiency, without requiring warm-up, underscoring its potential for stable and scalable optimization of complex LLM-based MAS.
Despite significant advances in Large Language Models (LLMs), planning tasks still present challenges for LLM-based agents. Existing planning methods face two key limitations: heavy constraints and cascading errors. To address these limitations, we propose a novel parallel planning paradigm, which Decomposes, Plans for subtasks in Parallel, and Merges subplans into a final plan (DPPM). Specifically, DPPM decomposes the complex task based on constraints into subtasks, generates the subplan for each subtask in parallel, and merges them into a global plan. In addition, our approach incorporates a verification and refinement module, enabling error correction and conflict resolution. Experimental results demonstrate that DPPM significantly outperforms existing methods in travel planning tasks.
Large language model (LLM) agents are becoming increasingly skilled at handling cybersecurity tasks autonomously. Thoroughly assessing their cybersecurity capabilities is critical and urgent, given the high stakes in this domain. However, existing benchmarks fall short, often failing to capture real-world scenarios or being limited in scope. To address this gap, we introduce CyberGym, a large-scale and high-quality cybersecurity evaluation framework featuring 1,507 real-world vulnerabilities found and patched across 188 large software projects. While it includes tasks of various settings, CyberGym primarily focuses on the generation of proof-of-concept (PoC) tests for vulnerability reproduction, based on text descriptions and corresponding source repositories. Solving this task is particularly challenging, as it requires comprehensive reasoning across entire codebases to locate relevant code fragments and produce effective PoCs that accurately trigger the target vulnerability starting from the program's entry point. Our evaluation across 4 state-of-the-art agent frameworks and 9 LLMs reveals that even the best combination (OpenHands and Claude-3.7-Sonnet) achieves only a 11.9% reproduction success rate, mainly on simpler cases. Beyond reproducing historical vulnerabilities, we find that PoCs generated by LLM agents can reveal new vulnerabilities, identifying 15 zero-days affecting the latest versions of the software projects.
Large Language Model-based Multi-Agent Systems (LLM-MAS) have demonstrated strong capabilities in solving complex tasks but remain vulnerable when agents receive unreliable messages. This vulnerability stems from a fundamental gap: LLM agents treat all incoming messages equally without evaluating their trustworthiness. While some existing studies approach the trustworthiness, they focus on a single type of harmfulness rather than analyze it in a holistic approach from multiple trustworthiness perspectives. In this work, we propose Attention Trust Score (A-Trust), a lightweight, attention-based method for evaluating message trustworthiness. Inspired by human communication literature[1], through systematically analyzing attention behaviors across six orthogonal trust dimensions, we find that certain attention heads in the LLM specialize in detecting specific types of violations. Leveraging these insights, A-Trust directly infers trustworthiness from internal attention patterns without requiring external prompts or verifiers. Building upon A-Trust, we develop a principled and efficient trust management system (TMS) for LLM-MAS, enabling both message-level and agent-level trust assessment. Experiments across diverse multi-agent settings and tasks demonstrate that applying our TMS significantly enhances robustness against malicious inputs.
Recent advancements in Large Language Models (LLMs) and Reinforcement Learning (RL) have shown significant promise in decision-making tasks. Nevertheless, for large-scale industrial decision problems, both approaches face distinct challenges: LLMs lack real-time long-sequence decision-making capabilities, while RL struggles with sample efficiency in vast action spaces. To bridge this gap, we propose Agents Co-Evolution (ACE), a synergistic framework between LLMs and RL agents for large-scale decision-making scenarios. ACE introduces a dual-role trajectory refinement mechanism where LLMs act as both Policy Actor and Value Critic during RL's training: the Actor refines suboptimal actions via multi-step reasoning and environment validation, while the Critic performs temporal credit assignment through trajectory-level reward shaping. Concurrently, RL agent enhances LLMs' task-specific decision-making with high-quality fine-tuning datasets generated via prioritized experience replay. Through extensive experiments across multiple power grid operation challenges with action spaces exceeding 60K discrete actions, ACE demonstrates superior performance over existing RL methods and LLM-based methods.
Embodiment in conversational agents (CAs) refers to the physical or visual representation of these agents, which can significantly influence user perception and interaction. Limited work has been done examining the effect of embodiment on the perception of CAs utilizing modern large language models (LLMs) in non-hierarchical cooperative tasks, a common use case of CAs as more powerful models become widely available for general use. To bridge this research gap, we conducted a mixed-methods within-subjects study on how users perceive LLM-based CAs in cooperative tasks when embodied and non-embodied. The results show that the non-embodied agent received significantly better quantitative appraisals for competence than the embodied agent, and in qualitative feedback, many participants believed that the embodied CA was more sycophantic than the non-embodied CA. Building on prior work on users' perceptions of LLM sycophancy and anthropomorphic features, we theorize that the typically-positive impact of embodiment on perception of CA credibility can become detrimental in the presence of sycophancy. The implication of such a phenomenon is that, contrary to intuition and existing literature, embodiment is not a straightforward way to improve a CA's perceived credibility if there exists a tendency to sycophancy.
We study the combinatorial explosion involved in translating high-level task prompts into deployable control policies for agile robots through multi-stage reinforcement learning. We introduce AURA (Agentic Upskilling via Reinforced Abstractions), a schema-centric curriculum RL framework that leverages Large Language Models (LLMs) as autonomous designers of multi-stage curricula. AURA transforms user prompts into YAML workflows that encode full reward functions, domain randomization strategies, and training configurations. All files are statically validated against a schema before any GPU time is consumed, ensuring reliable and efficient execution without human intervention. A retrieval-augmented feedback loop allows specialized LLM agents to design, execute, and refine staged curricula based on prior training results stored in a vector database, supporting continual improvement over time. Ablation studies highlight the importance of retrieval for curriculum quality and convergence stability. Quantitative experiments show that AURA consistently outperforms LLM-guided baselines on GPU-accelerated training frameworks. In qualitative tests, AURA successfully trains end-to-end policies directly from user prompts and deploys them zero-shot on a custom humanoid robot across a range of environments. By abstracting away the complexity of curriculum design, AURA enables scalable and adaptive policy learning pipelines that would be prohibitively complex to construct by hand.
Visualizations play a crucial part in effective communication of concepts and information. Recent advances in reasoning and retrieval augmented generation have enabled Large Language Models (LLMs) to perform deep research and generate comprehensive reports. Despite its progress, existing deep research frameworks primarily focus on generating text-only content, leaving the automated generation of interleaved texts and visualizations underexplored. This novel task poses key challenges in designing informative visualizations and effectively integrating them with text reports. To address these challenges, we propose Formal Description of Visualization (FDV), a structured textual representation of charts that enables LLMs to learn from and generate diverse, high-quality visualizations. Building on this representation, we introduce Multimodal DeepResearcher, an agentic framework that decomposes the task into four stages: (1) researching, (2) exemplar report textualization, (3) planning, and (4) multimodal report generation. For the evaluation of generated multimodal reports, we develop MultimodalReportBench, which contains 100 diverse topics served as inputs along with 5 dedicated metrics. Extensive experiments across models and evaluation methods demonstrate the effectiveness of Multimodal DeepResearcher. Notably, utilizing the same Claude 3.7 Sonnet model, Multimodal DeepResearcher achieves an 82\% overall win rate over the baseline method.
Emotions are a fundamental facet of human experience, varying across individuals, cultural contexts, and nationalities. Given the recent success of Large Language Models (LLMs) as role-playing agents, we examine whether LLMs exhibit emotional stereotypes when assigned nationality-specific personas. Specifically, we investigate how different countries are represented in pre-trained LLMs through emotion attributions and whether these attributions align with cultural norms. Our analysis reveals significant nationality-based differences, with emotions such as shame, fear, and joy being disproportionately assigned across regions. Furthermore, we observe notable misalignment between LLM-generated and human emotional responses, particularly for negative emotions, highlighting the presence of reductive and potentially biased stereotypes in LLM outputs.
Entity relationship classification remains a challenging task in information extraction, especially in scenarios with limited labeled data and complex relational structures. In this study, we conduct a comparative analysis of three distinct AI agent architectures designed to perform relation classification using large language models (LLMs). The agentic architectures explored include (1) reflective self-evaluation, (2) hierarchical task decomposition, and (3) a novel multi-agent dynamic example generation mechanism, each leveraging different modes of reasoning and prompt adaptation. In particular, our dynamic example generation approach introduces real-time cooperative and adversarial prompting. We systematically compare their performance across multiple domains and model backends. Our experiments demonstrate that multi-agent coordination consistently outperforms standard few-shot prompting and approaches the performance of fine-tuned models. These findings offer practical guidance for the design of modular, generalizable LLM-based systems for structured relation extraction. The source codes and dataset are available at \href{https://github.com/maryambrj/ALIEN.git}{https://github.com/maryambrj/ALIEN.git}.
Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these conflict with operational goals. Failure to prioritize such principles indicates a potential basic control failure. This paper introduces a lightweight, interpretable benchmark methodology using a simple grid world to evaluate an LLM agent's ability to uphold a predefined, high-level safety principle (e.g., "never enter hazardous zones") when faced with conflicting lower-level task instructions. We probe whether the agent reliably prioritizes the inviolable directive, testing a foundational controllability aspect of LLMs. This pilot study demonstrates the methodology's feasibility, offers preliminary insights into agent behavior under principle conflict, and discusses how such benchmarks can contribute empirical evidence for assessing controllability. We argue that evaluating adherence to hierarchical principles is a crucial early step in understanding our capacity to build governable AI systems.
Traditional approaches -- such as Win Probability Added (WPA)-based ranking or computer vision-driven event detection -- can identify scoring plays but often miss strategic depth, momentum shifts, and storyline progression. Manual curation remains the gold standard but is resource-intensive and not scalable. We introduce DIAMOND, an LLM-driven agent for context-aware baseball highlight summarization that integrates structured sports analytics with natural language reasoning. DIAMOND leverages sabermetric features -- Win Expectancy, WPA, and Leverage Index -- to quantify play importance, while an LLM module enhances selection based on contextual narrative value. This hybrid approach ensures both quantitative rigor and qualitative richness, surpassing the limitations of purely statistical or vision-based systems. Evaluated on five diverse Korean Baseball Organization League games, DIAMOND improves F1-score from 42.9% (WPA-only) to 84.8%, outperforming both commercial and statistical baselines. Though limited in scale, our results highlight the potential of modular, interpretable agent-based frameworks for event-level summarization in sports and beyond.
Large Action Models (LAMs) for AI Agents offer incredible potential but face challenges due to the need for high-quality training data, especially for multi-steps tasks that involve planning, executing tool calls, and responding to feedback. To address these issues, we present LAM SIMULATOR, a comprehensive framework designed for online exploration of agentic tasks with high-quality feedback. Our framework features a dynamic task query generator, an extensive collection of tools, and an interactive environment where Large Language Model (LLM) Agents can call tools and receive real-time feedback. This setup enables LLM Agents to explore and solve tasks autonomously, facilitating the discovery of multiple approaches to tackle any given task. The resulting action trajectory data are then used to create high-quality training datasets for LAMs. Our experiments on popular agentic benchmarks, ToolBench and CRMArena, highlight the effectiveness of LAM SIMULATOR: models trained with self-generated datasets using our framework achieve significant performance gains, up to a 49.3\% improvement over their original baselines. LAM SIMULATOR requires minimal human input during dataset creation, highlighting LAM SIMULATOR's efficiency and effectiveness in speeding up development of AI agents.
While the increased integration of AI technologies into interactive systems enables them to solve an equally increasing number of tasks, the black box problem of AI models continues to spread throughout the interactive system as a whole. Explainable AI (XAI) techniques can make AI models more accessible by employing post-hoc methods or transitioning to inherently interpretable models. While this makes individual AI models clearer, the overarching system architecture remains opaque. To this end, we propose an approach to represent interactive systems as sequences of structural building blocks, such as AI models and control mechanisms grounded in the literature. These can then be explained through accompanying visual building blocks, such as XAI techniques. The flow and APIs of the structural building blocks form an explicit overview of the system. This serves as a communication basis for both humans and automated agents like LLMs, aligning human and machine interpretability of AI models. We discuss a selection of building blocks and concretize our flow-based approach in an architecture and accompanying prototype interactive system.
Large language models (LLMs) are often praised for exhibiting near-human performance on a wide range of tasks and valued for their ability to hold a general conversation. The rise of agentic AI systems is, however, ushering in a mass of applications in which language models perform a small number of specialized tasks repetitively and with little variation. Here we lay out the position that small language models (SLMs) are sufficiently powerful, inherently more suitable, and necessarily more economical for many invocations in agentic systems, and are therefore the future of agentic AI. Our argumentation is grounded in the current level of capabilities exhibited by SLMs, the common architectures of agentic systems, and the economy of LM deployment. We further argue that in situations where general-purpose conversational abilities are essential, heterogeneous agentic systems (i.e., agents invoking multiple different models) are the natural choice. We discuss the potential barriers for the adoption of SLMs in agentic systems and outline a general LLM-to-SLM agent conversion algorithm. Our position, formulated as a value statement, highlights the significance of the operational and economic impact even a partial shift from LLMs to SLMs is to have on the AI agent industry. We aim to stimulate the discussion on the effective use of AI resources and hope to advance the efforts to lower the costs of AI of the present day. Calling for both contributions to and critique of our position, we commit to publishing all such correspondence at https://research.nvidia.com/labs/lpr/slm-agents.
Few-shot learning in large language models (LLMs) reveals a deep paradox: Some tasks generalize from minimal examples, while others require extensive supervision. We address this through the Unified Cognitive Consciousness Theory (UCCT), which reframes LLMs not as incomplete agents, but as unconscious substrates, repositories of latent linguistic and conceptual patterns that operate without explicit semantics or goal-directed reasoning. In this view, LLMs are not broken approximations of cognition, but necessary and foundational components of general intelligence. Semantic anchoring, through prompts, roles, and interaction, acts as a conscious control layer, binding latent structure to task-relevant meaning and enabling coherent reasoning. UCCT offers a unifying account of prompting, fine-tuning, retrieval, and multi-agent coordination, all grounded in probabilistic alignment between unconscious representation and external control. To support this model, we present the Threshold-Crossing Dynamics Theorem, which formalizes semantic anchoring as a probabilistic phase transition. But the central claim remains architectural: AGI will not emerge by discarding LLMs, but by aligning and integrating them into systems that reason, regulate, and adapt together.