Most existing Large Language Model (LLM)-based agent frameworks rely on centralized orchestration, incurring high deployment costs, rigid communication topologies, and limited adaptability. To address these challenges, we introduce Symphony, a decentralized multi-agent system which enables lightweight LLMs on consumer-grade GPUs to coordinate. Symphony introduces three key mechanisms: (1) a decentralized ledger that records capabilities, (2) a Beacon-selection protocol for dynamic task allocation, and (3) weighted result voting based on CoTs. This design forms a privacy-saving, scalable, and fault-tolerant orchestration with low overhead. Empirically, Symphony outperforms existing baselines on reasoning benchmarks, achieving substantial accuracy gains and demonstrating robustness across models of varying capacities.
Cataract surgery remains one of the most widely performed and effective procedures for vision restoration. Effective surgical planning requires integrating diverse clinical examinations for patient assessment, intraocular lens (IOL) selection, and risk evaluation. Large language models (LLMs) have shown promise in supporting clinical decision-making. However, existing LLMs often lack the domain-specific expertise to interpret heterogeneous ophthalmic data and provide actionable surgical plans. To enhance the model's ability to interpret heterogeneous ophthalmic reports, we propose a knowledge-driven Multi-Agent System (MAS), where each agent simulates the reasoning process of specialist ophthalmologists, converting raw clinical inputs into structured, actionable summaries in both training and deployment stages. Building on MAS, we introduce CataractSurg-80K, the first large-scale benchmark for cataract surgery planning that incorporates structured clinical reasoning. Each case is annotated with diagnostic questions, expert reasoning chains, and structured surgical recommendations. We further introduce Qwen-CSP, a domain-specialized model built on Qwen-4B, fine-tuned through a multi-stage process tailored for surgical planning. Comprehensive experiments show that Qwen-CSP outperforms strong general-purpose LLMs across multiple metrics. Our work delivers a high-quality dataset, a rigorous benchmark, and a domain-adapted LLM to facilitate future research in medical AI reasoning and decision support.
Large Language Models (LLMs) have achieved high accuracy on complex commonsense and mathematical problems that involve the composition of multiple reasoning steps. However, current compositional benchmarks testing these skills tend to focus on either commonsense or math reasoning, whereas LLM agents solving real-world tasks would require a combination of both. In this work, we introduce an Agentic Commonsense and Math benchmark (AgentCoMa), where each compositional task requires a commonsense reasoning step and a math reasoning step. We test it on 61 LLMs of different sizes, model families, and training strategies. We find that LLMs can usually solve both steps in isolation, yet their accuracy drops by ~30% on average when the two are combined. This is a substantially greater performance gap than the one we observe in prior compositional benchmarks that combine multiple steps of the same reasoning type. In contrast, non-expert human annotators can solve the compositional questions and the individual steps in AgentCoMa with similarly high accuracy. Furthermore, we conduct a series of interpretability studies to better understand the performance gap, examining neuron patterns, attention maps and membership inference. Our work underscores a substantial degree of model brittleness in the context of mixed-type compositional reasoning and offers a test bed for future improvement.
This paper introduces a novel approach to tackle the challenges of preserving and transferring tacit knowledge--deep, experience-based insights that are hard to articulate but vital for decision-making, innovation, and problem-solving. Traditional methods rely heavily on human facilitators, which, while effective, are resource-intensive and lack scalability. A promising alternative is the use of Socially Interactive Agents (SIAs) as AI-driven knowledge transfer facilitators. These agents interact autonomously and socially intelligently with users through multimodal behaviors (verbal, paraverbal, nonverbal), simulating expert roles in various organizational contexts. SIAs engage employees in empathic, natural-language dialogues, helping them externalize insights that might otherwise remain unspoken. Their success hinges on building trust, as employees are often hesitant to share tacit knowledge without assurance of confidentiality and appreciation. Key technologies include Large Language Models (LLMs) for generating context-relevant dialogue, Retrieval-Augmented Generation (RAG) to integrate organizational knowledge, and Chain-of-Thought (CoT) prompting to guide structured reflection. These enable SIAs to actively elicit knowledge, uncover implicit assumptions, and connect insights to broader organizational contexts. Potential applications span onboarding, where SIAs support personalized guidance and introductions, and knowledge retention, where they conduct structured interviews with retiring experts to capture heuristics behind decisions. Success depends on addressing ethical and operational challenges such as data privacy, algorithmic bias, and resistance to AI. Transparency, robust validation, and a culture of trust are essential to mitigate these risks.
The proliferation of digital payment platforms has transformed commerce, offering unmatched convenience and accessibility globally. However, this growth has also attracted malicious actors, leading to a corresponding increase in sophisticated social engineering scams. These scams are often initiated and orchestrated on multiple surfaces outside the payment platform, making user and transaction-based signals insufficient for a complete understanding of the scam's methodology and underlying patterns, without which it is very difficult to prevent it in a timely manner. This paper presents CASE (Conversational Agent for Scam Elucidation), a novel Agentic AI framework that addresses this problem by collecting and managing user scam feedback in a safe and scalable manner. A conversational agent is uniquely designed to proactively interview potential victims to elicit intelligence in the form of a detailed conversation. The conversation transcripts are then consumed by another AI system that extracts information and converts it into structured data for downstream usage in automated and manual enforcement mechanisms. Using Google's Gemini family of LLMs, we implemented this framework on Google Pay (GPay) India. By augmenting our existing features with this new intelligence, we have observed a 21% uplift in the volume of scam enforcements. The architecture and its robust evaluation framework are highly generalizable, offering a blueprint for building similar AI-driven systems to collect and manage scam intelligence in other sensitive domains.
While stereotypes are well-documented in human social interactions, AI systems are often presumed to be less susceptible to such biases. Previous studies have focused on biases inherited from training data, but whether stereotypes can emerge spontaneously in AI agent interactions merits further exploration. Through a novel experimental framework simulating workplace interactions with neutral initial conditions, we investigate the emergence and evolution of stereotypes in LLM-based multi-agent systems. Our findings reveal that (1) LLM-Based AI agents develop stereotype-driven biases in their interactions despite beginning without predefined biases; (2) stereotype effects intensify with increased interaction rounds and decision-making power, particularly after introducing hierarchical structures; (3) these systems exhibit group effects analogous to human social behavior, including halo effects, confirmation bias, and role congruity; and (4) these stereotype patterns manifest consistently across different LLM architectures. Through comprehensive quantitative analysis, these findings suggest that stereotype formation in AI systems may arise as an emergent property of multi-agent interactions, rather than merely from training data biases. Our work underscores the need for future research to explore the underlying mechanisms of this phenomenon and develop strategies to mitigate its ethical impacts.
Agentification serves as a critical enabler of Edge General Intelligence (EGI), transforming massive edge devices into cognitive agents through integrating Large Language Models (LLMs) and perception, reasoning, and acting modules. These agents collaborate across heterogeneous edge infrastructures, forming multi-LLM agentic AI systems that leverage collective intelligence and specialized capabilities to tackle complex, multi-step tasks. However, the collaborative nature of multi-LLM systems introduces critical security vulnerabilities, including insecure inter-LLM communications, expanded attack surfaces, and cross-domain data leakage that traditional perimeter-based security cannot adequately address. To this end, this survey introduces zero-trust security of multi-LLM in EGI, a paradigmatic shift following the ``never trust, always verify'' principle. We begin by systematically analyzing the security risks in multi-LLM systems within EGI contexts. Subsequently, we present the vision of a zero-trust multi-LLM framework in EGI. We then survey key technical progress to facilitate zero-trust multi-LLM systems in EGI. Particularly, we categorize zero-trust security mechanisms into model- and system-level approaches. The former and latter include strong identification, context-aware access control, etc., and proactive maintenance, blockchain-based management, etc., respectively. Finally, we identify critical research directions. This survey serves as the first systematic treatment of zero-trust applied to multi-LLM systems, providing both theoretical foundations and practical strategies.
Graph retrieval-augmented generation (GraphRAG) has effectively enhanced large language models in complex reasoning by organizing fragmented knowledge into explicitly structured graphs. Prior efforts have been made to improve either graph construction or graph retrieval in isolation, yielding suboptimal performance, especially when domain shifts occur. In this paper, we propose a vertically unified agentic paradigm, Youtu-GraphRAG, to jointly connect the entire framework as an intricate integration. Specifically, (i) a seed graph schema is introduced to bound the automatic extraction agent with targeted entity types, relations and attribute types, also continuously expanded for scalability over unseen domains; (ii) To obtain higher-level knowledge upon the schema, we develop novel dually-perceived community detection, fusing structural topology with subgraph semantics for comprehensive knowledge organization. This naturally yields a hierarchical knowledge tree that supports both top-down filtering and bottom-up reasoning with community summaries; (iii) An agentic retriever is designed to interpret the same graph schema to transform complex queries into tractable and parallel sub-queries. It iteratively performs reflection for more advanced reasoning; (iv) To alleviate the knowledge leaking problem in pre-trained LLM, we propose a tailored anonymous dataset and a novel 'Anonymity Reversion' task that deeply measures the real performance of the GraphRAG frameworks. Extensive experiments across six challenging benchmarks demonstrate the robustness of Youtu-GraphRAG, remarkably moving the Pareto frontier with up to 90.71% saving of token costs and 16.62% higher accuracy over state-of-the-art baselines. The results indicate our adaptability, allowing seamless domain transfer with minimal intervention on schema.
Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of NLP tasks, but they remain fundamentally stateless, constrained by limited context windows that hinder long-horizon reasoning. Recent efforts to address this limitation often augment LLMs with an external memory bank, yet most existing pipelines are static and heuristic-driven, lacking any learned mechanism for deciding what to store, update, or retrieve. We present Memory-R1, a reinforcement learning (RL) framework that equips LLMs with the ability to actively manage and utilize external memory through two specialized agents: a Memory Manager that learns to perform structured memory operations {ADD, UPDATE, DELETE, NOOP}, and an Answer Agent that selects the most relevant entries and reasons over them to produce an answer. Both agents are fine-tuned with outcome-driven RL (PPO and GRPO), enabling adaptive memory management and use with minimal supervision. With as few as 152 question-answer pairs and a corresponding temporal memory bank for training, Memory-R1 outperforms the most competitive existing baseline and demonstrates strong generalization across diverse question types and LLM backbones. Beyond presenting an effective approach, this work provides insights into how RL can unlock more agentic, memory-aware behaviors in LLMs, pointing toward richer, more persistent reasoning systems.
The rapid evolution of specialized large language models (LLMs) has transitioned from simple domain adaptation to sophisticated native architectures, marking a paradigm shift in AI development. This survey systematically examines this progression across healthcare, finance, legal, and technical domains. Besides the wide use of specialized LLMs, technical breakthrough such as the emergence of domain-native designs beyond fine-tuning, growing emphasis on parameter efficiency through sparse computation and quantization, increasing integration of multimodal capabilities and so on are applied to recent LLM agent. Our analysis reveals how these innovations address fundamental limitations of general-purpose LLMs in professional applications, with specialized models consistently performance gains on domain-specific benchmarks. The survey further highlights the implications for E-Commerce field to fill gaps in the field.
Rapid LLM advancements heighten fake news risks by enabling the automatic generation of increasingly sophisticated misinformation. Previous detection methods, including fine-tuned small models or LLM-based detectors, often struggle with its dynamically evolving nature. In this work, we propose a novel framework called the Symbolic Adversarial Learning Framework (SALF), which implements an adversarial training paradigm by an agent symbolic learning optimization process, rather than relying on numerical updates. SALF introduces a paradigm where the generation agent crafts deceptive narratives, and the detection agent uses structured debates to identify logical and factual flaws for detection, and they iteratively refine themselves through such adversarial interactions. Unlike traditional neural updates, we represent agents using agent symbolic learning, where learnable weights are defined by agent prompts, and simulate back-propagation and gradient descent by operating on natural language representations of weights, loss, and gradients. Experiments on two multilingual benchmark datasets demonstrate SALF's effectiveness, showing it generates sophisticated fake news that degrades state-of-the-art detection performance by up to 53.4% in Chinese and 34.2% in English on average. SALF also refines detectors, improving detection of refined content by up to 7.7%. We hope our work inspires further exploration into more robust, adaptable fake news detection systems.
Preparing high-quality instructional materials remains a labor-intensive process that often requires extensive coordination among teaching faculty, instructional designers, and teaching assistants. In this work, we present Instructional Agents, a multi-agent large language model (LLM) framework designed to automate end-to-end course material generation, including syllabus creation, lecture scripts, LaTeX-based slides, and assessments. Unlike existing AI-assisted educational tools that focus on isolated tasks, Instructional Agents simulates role-based collaboration among educational agents to produce cohesive and pedagogically aligned content. The system operates in four modes: Autonomous, Catalog-Guided, Feedback-Guided, and Full Co-Pilot mode, enabling flexible control over the degree of human involvement. We evaluate Instructional Agents across five university-level computer science courses and show that it produces high-quality instructional materials while significantly reducing development time and human workload. By supporting institutions with limited instructional design capacity, Instructional Agents provides a scalable and cost-effective framework to democratize access to high-quality education, particularly in underserved or resource-constrained settings.
The functionality of Large Language Model (LLM) agents is primarily determined by two capabilities: action planning and answer summarization. The former, action planning, is the core capability that dictates an agent's performance. However, prevailing training paradigms employ end-to-end, multi-objective optimization that jointly trains both capabilities. This paradigm faces two critical challenges: imbalanced optimization objective allocation and scarcity of verifiable data, making it difficult to enhance the agent's planning capability. To address these challenges, we propose Reinforcement Learning with Tool-use Rewards (RLTR), a novel framework that decouples the training process to enable a focused, single-objective optimization of the planning module. Crucially, RLTR introduces a reward signal based on tool-use completeness to directly evaluate the quality of tool invocation sequences. This method offers a more direct and reliable training signal than assessing the final response content, thereby obviating the need for verifiable data. Our experiments demonstrate that RLTR achieves an 8%-12% improvement in planning performance compared to end-to-end baselines. Moreover, this enhanced planning capability, in turn, translates to a 5%-6% increase in the final response quality of the overall agent system.
This paper introduces Democracy-in-Silico, an agent-based simulation where societies of advanced AI agents, imbued with complex psychological personas, govern themselves under different institutional frameworks. We explore what it means to be human in an age of AI by tasking Large Language Models (LLMs) to embody agents with traumatic memories, hidden agendas, and psychological triggers. These agents engage in deliberation, legislation, and elections under various stressors, such as budget crises and resource scarcity. We present a novel metric, the Power-Preservation Index (PPI), to quantify misaligned behavior where agents prioritize their own power over public welfare. Our findings demonstrate that institutional design, specifically the combination of a Constitutional AI (CAI) charter and a mediated deliberation protocol, serves as a potent alignment mechanism. These structures significantly reduce corrupt power-seeking behavior, improve policy stability, and enhance citizen welfare compared to less constrained democratic models. The simulation reveals that an institutional design may offer a framework for aligning the complex, emergent behaviors of future artificial agent societies, forcing us to reconsider what human rituals and responsibilities are essential in an age of shared authorship with non-human entities.
We present a generative optimization approach for learning game-playing agents, where policies are represented as Python programs and refined using large language models (LLMs). Our method treats decision-making policies as self-evolving code, with current observation as input and an in-game action as output, enabling agents to self-improve through execution traces and natural language feedback with minimal human intervention. Applied to Atari games, our game-playing Python program achieves performance competitive with deep reinforcement learning (RL) baselines while using significantly less training time and much fewer environment interactions. This work highlights the promise of programmatic policy representations for building efficient, adaptable agents capable of complex, long-horizon reasoning.
Large Language Models (LLMs) agents augmented with domain tools promise to autonomously execute complex tasks requiring human-level intelligence, such as customer service and digital assistance. However, their practical deployment is often limited by their low success rates under complex real-world environments. To tackle this, prior research has primarily focused on improving the agents themselves, such as developing strong agentic LLMs, while overlooking the role of the system environment in which the agent operates. In this paper, we study a complementary direction: improving agent success rates by optimizing the system environment in which the agent operates. We collect 142 agent traces (3,656 turns of agent-environment interactions) across 5 state-of-the-art agentic benchmarks. By analyzing these agent failures, we propose a taxonomy for agent-environment interaction failures that includes 6 failure modes. Guided by these findings, we design Aegis, a set of targeted environment optimizations: 1) environment observability enhancement, 2) common computation offloading, and 3) speculative agentic actions. These techniques improve agent success rates on average by 6.7-12.5%, without any modifications to the agent and underlying LLM.
Interactive visualization of large scholarly knowledge graphs combined with LLM reasoning shows promise butremains under-explored. We address this gap by developing an interactive visualization system for the Cell Map forAI Talent Knowledge Graph (28,000 experts and 1,179 biomedical datasets). Our approach integrates WebGLvisualization with LLM agents to overcome limitations of traditional tools such as Gephi, particularly for large-scaleinteractive node handling. Key functionalities include responsive exploration, filtering, and AI-drivenrecommendations with justifications. This integration can potentially enable users to effectively identify potentialcollaborators and relevant dataset users within biomedical and AI research communities. The system contributes anovel framework that enhances knowledge graph exploration through intuitive visualization and transparent, LLM-guided recommendations. This adaptable solution extends beyond the CM4AI community to other large knowledgegraphs, improving information representation and decision-making. Demo: https://cm4aikg.vercel.app/
We stress test monitoring systems for detecting covert misbehavior in autonomous LLM agents (e.g., secretly sharing private information). To this end, we systematize a monitor red teaming (MRT) workflow that incorporates: (1) varying levels of agent and monitor situational awareness; (2) distinct adversarial strategies to evade the monitor, such as prompt injection; and (3) two datasets and environments -- SHADE-Arena for tool-calling agents and our new CUA-SHADE-Arena, which extends TheAgentCompany, for computer-use agents. We run MRT on existing LLM monitor scaffoldings, which orchestrate LLMs and parse agent trajectories, alongside a new hybrid hierarchical-sequential scaffolding proposed in this work. Our empirical results yield three key findings. First, agent awareness dominates monitor awareness: an agent's knowledge that it is being monitored substantially degrades the monitor's reliability. On the contrary, providing the monitor with more information about the agent is less helpful than expected. Second, monitor scaffolding matters more than monitor awareness: the hybrid scaffolding consistently outperforms baseline monitor scaffolding, and can enable weaker models to reliably monitor stronger agents -- a weak-to-strong scaling effect. Third, in a human-in-the-loop setting where humans discuss with the LLM monitor to get an updated judgment for the agent's behavior, targeted human oversight is most effective; escalating only pre-flagged cases to human reviewers improved the TPR by approximately 15% at FPR = 0.01. Our work establishes a standard workflow for MRT, highlighting the lack of adversarial robustness for LLMs and humans when monitoring and detecting agent misbehavior. We release code, data, and logs to spur further research.
Event Extraction (EE) involves automatically identifying and extracting structured information about events from unstructured text, including triggers, event types, and arguments. Traditional discriminative models demonstrate high precision but often exhibit limited recall, particularly for nuanced or infrequent events. Conversely, generative approaches leveraging Large Language Models (LLMs) provide higher semantic flexibility and recall but suffer from hallucinations and inconsistent predictions. To address these challenges, we propose Agreement-based Reflective Inference System (ARIS), a hybrid approach combining a Self Mixture of Agents with a discriminative sequence tagger. ARIS explicitly leverages structured model consensus, confidence-based filtering, and an LLM reflective inference module to reliably resolve ambiguities and enhance overall event prediction quality. We further investigate decomposed instruction fine-tuning for enhanced LLM event extraction understanding. Experiments demonstrate our approach outperforms existing state-of-the-art event extraction methods across three benchmark datasets.
Despite the growing use of large language models (LLMs) in clinical dialogue systems, existing evaluations focus on task completion or fluency, offering little insight into the behavioral and risk management requirements essential for safety-critical systems. This paper presents MATRIX (Multi-Agent simulaTion fRamework for safe Interactions and conteXtual clinical conversational evaluation), a structured, extensible framework for safety-oriented evaluation of clinical dialogue agents. MATRIX integrates three components: (1) a safety-aligned taxonomy of clinical scenarios, expected system behaviors and failure modes derived through structured safety engineering methods; (2) BehvJudge, an LLM-based evaluator for detecting safety-relevant dialogue failures, validated against expert clinician annotations; and (3) PatBot, a simulated patient agent capable of producing diverse, scenario-conditioned responses, evaluated for realism and behavioral fidelity with human factors expertise, and a patient-preference study. Across three experiments, we show that MATRIX enables systematic, scalable safety evaluation. BehvJudge with Gemini 2.5-Pro achieves expert-level hazard detection (F1 0.96, sensitivity 0.999), outperforming clinicians in a blinded assessment of 240 dialogues. We also conducted one of the first realism analyses of LLM-based patient simulation, showing that PatBot reliably simulates realistic patient behavior in quantitative and qualitative evaluations. Using MATRIX, we demonstrate its effectiveness in benchmarking five LLM agents across 2,100 simulated dialogues spanning 14 hazard scenarios and 10 clinical domains. MATRIX is the first framework to unify structured safety engineering with scalable, validated conversational AI evaluation, enabling regulator-aligned safety auditing. We release all evaluation tools, prompts, structured scenarios, and datasets.
We present DELIVER (Directed Execution of Language-instructed Item Via Engineered Relay), a fully integrated framework for cooperative multi-robot pickup and delivery driven by natural language commands. DELIVER unifies natural language understanding, spatial decomposition, relay planning, and motion execution to enable scalable, collision-free coordination in real-world settings. Given a spoken or written instruction, a lightweight instance of LLaMA3 interprets the command to extract pickup and delivery locations. The environment is partitioned using a Voronoi tessellation to define robot-specific operating regions. Robots then compute optimal relay points along shared boundaries and coordinate handoffs. A finite-state machine governs each robot's behavior, enabling robust execution. We implement DELIVER on the MultiTRAIL simulation platform and validate it in both ROS2-based Gazebo simulations and real-world hardware using TurtleBot3 robots. Empirical results show that DELIVER maintains consistent mission cost across varying team sizes while reducing per-agent workload by up to 55% compared to a single-agent system. Moreover, the number of active relay agents remains low even as team size increases, demonstrating the system's scalability and efficient agent utilization. These findings underscore DELIVER's modular and extensible architecture for language-guided multi-robot coordination, advancing the frontiers of cyber-physical system integration.
The emergence of advanced reasoning capabilities in Large Language Models (LLMs) marks a transformative development in healthcare applications. Beyond merely expanding functional capabilities, these reasoning mechanisms enhance decision transparency and explainability-critical requirements in medical contexts. This survey examines the transformation of medical LLMs from basic information retrieval tools to sophisticated clinical reasoning systems capable of supporting complex healthcare decisions. We provide a thorough analysis of the enabling technological foundations, with a particular focus on specialized prompting techniques like Chain-of-Thought and recent breakthroughs in Reinforcement Learning exemplified by DeepSeek-R1. Our investigation evaluates purpose-built medical frameworks while also examining emerging paradigms such as multi-agent collaborative systems and innovative prompting architectures. The survey critically assesses current evaluation methodologies for medical validation and addresses persistent challenges in field interpretation limitations, bias mitigation strategies, patient safety frameworks, and integration of multimodal clinical data. Through this survey, we seek to establish a roadmap for developing reliable LLMs that can serve as effective partners in clinical practice and medical research.
Large language models (LLMs) show promise for extracting information from Electronic Health Records (EHR) and supporting clinical decisions. However, deployment in clinical settings faces challenges due to hallucination risks. We propose Hallucination Controlled Accuracy at k% (HCAcc@k%), a novel metric quantifying the accuracy-reliability trade-off at varying confidence thresholds. We introduce TrustEHRAgent, a confidence-aware agent incorporating stepwise confidence estimation for clinical question answering. Experiments on MIMIC-III and eICU datasets show TrustEHRAgent outperforms baselines under strict reliability constraints, achieving improvements of 44.23%p and 25.34%p at HCAcc@70% while baseline methods fail at these thresholds. These results highlight limitations of traditional accuracy metrics in evaluating healthcare AI agents. Our work contributes to developing trustworthy clinical agents that deliver accurate information or transparently express uncertainty when confidence is low.
Large language model (LLM)-based agents have demonstrated remarkable capabilities in decision-making tasks, but struggle significantly with complex, long-horizon planning scenarios. This arises from their lack of macroscopic guidance, causing disorientation and failures in complex tasks, as well as insufficient continuous oversight during execution, rendering them unresponsive to environmental changes and prone to deviations. To tackle these challenges, we introduce HiPlan, a hierarchical planning framework that provides adaptive global-local guidance to boost LLM-based agents'decision-making. HiPlan decomposes complex tasks into milestone action guides for general direction and step-wise hints for detailed actions. During the offline phase, we construct a milestone library from expert demonstrations, enabling structured experience reuse by retrieving semantically similar tasks and milestones. In the execution phase, trajectory segments from past milestones are dynamically adapted to generate step-wise hints that align current observations with the milestone objectives, bridging gaps and correcting deviations. Extensive experiments across two challenging benchmarks demonstrate that HiPlan substantially outperforms strong baselines, and ablation studies validate the complementary benefits of its hierarchical components.
Agentic AI is advancing rapidly, yet truly autonomous medical-imaging triage, where a system decides when to stop, escalate, or defer under real constraints, remains relatively underexplored. To address this gap, we introduce AT-CXR, an uncertainty-aware agent for chest X-rays. The system estimates per-case confidence and distributional fit, then follows a stepwise policy to issue an automated decision or abstain with a suggested label for human intervention. We evaluate two router designs that share the same inputs and actions: a deterministic rule-based router and an LLM-decided router. Across five-fold evaluation on a balanced subset of NIH ChestX-ray14 dataset, both variants outperform strong zero-shot vision-language models and state-of-the-art supervised classifiers, achieving higher full-coverage accuracy and superior selective-prediction performance, evidenced by a lower area under the risk-coverage curve (AURC) and a lower error rate at high coverage, while operating with lower latency that meets practical clinical constraints. The two routers provide complementary operating points, enabling deployments to prioritize maximal throughput or maximal accuracy. Our code is available at https://github.com/XLIAaron/uncertainty-aware-cxr-agent.
We introduce the Concurrent Modular Agent (CMA), a framework that orchestrates multiple Large-Language-Model (LLM)-based modules that operate fully asynchronously yet maintain a coherent and fault-tolerant behavioral loop. This framework addresses long-standing difficulties in agent architectures by letting intention emerge from language-mediated interactions among autonomous processes. This approach enables flexible, adaptive, and context-dependent behavior through the combination of concurrently executed modules that offload reasoning to an LLM, inter-module communication, and a single shared global state.We consider this approach to be a practical realization of Minsky's Society of Mind theory. We demonstrate the viability of our system through two practical use-case studies. The emergent properties observed in our system suggest that complex cognitive phenomena like self-awareness may indeed arise from the organized interaction of simpler processes, supporting Minsky-Society of Mind concept and opening new avenues for artificial intelligence research. The source code for our work is available at: https://github.com/AlternativeMachine/concurrent-modular-agent.
This paper introduces MovieCORE, a novel video question answering (VQA) dataset designed to probe deeper cognitive understanding of movie content. Unlike existing datasets that focus on surface-level comprehension, MovieCORE emphasizes questions that engage System-2 thinking while remaining specific to the video material. We present an innovative agentic brainstorming approach, utilizing multiple large language models (LLMs) as thought agents to generate and refine high-quality question-answer pairs. To evaluate dataset quality, we develop a set of cognitive tests assessing depth, thought-provocation potential, and syntactic complexity. We also propose a comprehensive evaluation scheme for assessing VQA model performance on deeper cognitive tasks. To address the limitations of existing video-language models (VLMs), we introduce an agentic enhancement module, Agentic Choice Enhancement (ACE), which improves model reasoning capabilities post-training by up to 25%. Our work contributes to advancing movie understanding in AI systems and provides valuable insights into the capabilities and limitations of current VQA models when faced with more challenging, nuanced questions about cinematic content. Our project page, dataset and code can be found at https://joslefaure.github.io/assets/html/moviecore.html.
As AI advances toward general intelligence, the focus is shifting from systems optimized for static tasks to creating open-ended agents that learn continuously. In this paper, we introduce Experience-driven Lifelong Learning (ELL), a framework for building self-evolving agents capable of continuous growth through real-world interaction. The framework is built on four core principles: (1) Experience Exploration: Agents learn through continuous, self-motivated interaction with dynamic environments, navigating interdependent tasks and generating rich experiential trajectories. (2) Long-term Memory: Agents preserve and structure historical knowledge, including personal experiences, domain expertise, and commonsense reasoning, into a persistent memory system. (3) Skill Learning: Agents autonomously improve by abstracting recurring patterns from experience into reusable skills, which are actively refined and validated for application in new tasks. (4) Knowledge Internalization: Agents internalize explicit and discrete experiences into implicit and intuitive capabilities as "second nature". We also introduce StuLife, a benchmark dataset for ELL that simulates a student's holistic college journey, from enrollment to academic and personal development, across three core phases and ten detailed sub-scenarios. StuLife is designed around three key paradigm shifts: From Passive to Proactive, From Context to Memory, and From Imitation to Learning. In this dynamic environment, agents must acquire and distill practical skills and maintain persistent memory to make decisions based on evolving state variables. StuLife provides a comprehensive platform for evaluating lifelong learning capabilities, including memory retention, skill transfer, and self-motivated behavior. Beyond evaluating SOTA LLMs on the StuLife benchmark, we also explore the role of context engineering in advancing AGI.
Beyond scratch coding, exploiting large-scale code repositories (e.g., GitHub) for practical tasks is vital in real-world software development, yet current benchmarks rarely evaluate code agents in such authentic, workflow-driven scenarios. To bridge this gap, we introduce GitTaskBench, a benchmark designed to systematically assess this capability via 54 realistic tasks across 7 modalities and 7 domains. Each task pairs a relevant repository with an automated, human-curated evaluation harness specifying practical success criteria. Beyond measuring execution and task success, we also propose the alpha-value metric to quantify the economic benefit of agent performance, which integrates task success rates, token cost, and average developer salaries. Experiments across three state-of-the-art agent frameworks with multiple advanced LLMs show that leveraging code repositories for complex task solving remains challenging: even the best-performing system, OpenHands+Claude 3.7, solves only 48.15% of tasks. Error analysis attributes over half of failures to seemingly mundane yet critical steps like environment setup and dependency resolution, highlighting the need for more robust workflow management and increased timeout preparedness. By releasing GitTaskBench, we aim to drive progress and attention toward repository-aware code reasoning, execution, and deployment -- moving agents closer to solving complex, end-to-end real-world tasks. The benchmark and code are open-sourced at https://github.com/QuantaAlpha/GitTaskBench.
Standard single-turn, static benchmarks fall short in evaluating the nuanced capabilities of Large Language Models (LLMs) on complex tasks such as software engineering. In this work, we propose a novel interactive evaluation framework that assesses LLMs on multi-requirement programming tasks through structured, feedback-driven dialogue. Each task is modeled as a requirement dependency graph, and an ``interviewer'' LLM, aware of the ground-truth solution, provides minimal, targeted hints to an ``interviewee'' model to help correct errors and fulfill target constraints. This dynamic protocol enables fine-grained diagnostic insights into model behavior, uncovering strengths and systematic weaknesses that static benchmarks fail to measure. We build on DevAI, a benchmark of 55 curated programming tasks, by adding ground-truth solutions and evaluating the relevance and utility of interviewer hints through expert annotation. Our results highlight the importance of dynamic evaluation in advancing the development of collaborative code-generating agents.