Large language models (LLMs) deliver superior performance but require substantial computational resources and operate with relatively low efficiency, while smaller models can efficiently handle simpler tasks with fewer resources. LLM routing is a crucial paradigm that dynamically selects the most suitable large language models from a pool of candidates to process diverse inputs, ensuring optimal resource utilization while maintaining response quality. Existing routing frameworks typically model this as a locally optimal decision-making problem, selecting the presumed best-fit LLM for each query individually, which overlook global budget constraints, resulting in ineffective resource allocation. To tackle this problem, we introduce OmniRouter, a fundamentally controllable routing framework for multi-LLM serving. Instead of making per-query greedy choices, OmniRouter models the routing task as a constrained optimization problem, assigning models that minimize total cost while ensuring the required performance level. Specifically, a hybrid retrieval-augmented predictor is designed to predict the capabilities and costs of LLMs and a constrained optimizer is employed to control globally optimal query-model allocation. Experiments show that OmniRouter achieves up to 6.30% improvement in response accuracy while simultaneously reducing computational costs by at least 10.15% compared to competitive router baselines. The code and the dataset are available at https://github.com/agiresearch/OmniRouter.
Explainable AI is increasingly employing argumentation methods to facilitate interactive explanations between AI agents and human users. While existing approaches typically rely on predetermined human user models, there remains a critical gap in dynamically learning and updating these models during interactions. In this paper, we present a framework that enables AI agents to adapt their understanding of human users through argumentation-based dialogues. Our approach, called Persona, draws on prospect theory and integrates a probability weighting function with a Bayesian belief update mechanism that refines a probability distribution over possible human models based on exchanged arguments. Through empirical evaluations with human users in an applied argumentation setting, we demonstrate that Persona effectively captures evolving human beliefs, facilitates personalized interactions, and outperforms state-of-the-art methods.
Scientific experimentation, a cornerstone of human progress, demands rigor in reliability, methodical control, and interpretability to yield meaningful results. Despite the growing capabilities of large language models (LLMs) in automating different aspects of the scientific process, automating rigorous experimentation remains a significant challenge. To address this gap, we propose Curie, an AI agent framework designed to embed rigor into the experimentation process through three key components: an intra-agent rigor module to enhance reliability, an inter-agent rigor module to maintain methodical control, and an experiment knowledge module to enhance interpretability. To evaluate Curie, we design a novel experimental benchmark composed of 46 questions across four computer science domains, derived from influential research papers, and widely adopted open-source projects. Compared to the strongest baseline tested, we achieve a 3.4$\times$ improvement in correctly answering experimental questions.Curie is open-sourced at https://github.com/Just-Curieous/Curie.
Multi-class cell segmentation in high-resolution gigapixel whole slide images (WSI) is crucial for various clinical applications. However, training such models typically requires labor-intensive, pixel-wise annotations by domain experts. Recent efforts have democratized this process by involving lay annotators without medical expertise. However, conventional non-agent-based approaches struggle to handle annotation noise adaptively, as they lack mechanisms to mitigate false positives (FP) and false negatives (FN) at both the image-feature and pixel levels. In this paper, we propose a consensus-aware self-corrective AI agent that leverages the Consensus Matrix to guide its learning process. The Consensus Matrix defines regions where both the AI and annotators agree on cell and non-cell annotations, which are prioritized with stronger supervision. Conversely, areas of disagreement are adaptively weighted based on their feature similarity to high-confidence agreement regions, with more similar regions receiving greater attention. Additionally, contrastive learning is employed to separate features of noisy regions from those of reliable agreement regions by maximizing their dissimilarity. This paradigm enables the AI to iteratively refine noisy labels, enhancing its robustness. Validated on one real-world lay-annotated cell dataset and two simulated noisy datasets, our method demonstrates improved segmentation performance, effectively correcting FP and FN errors and showcasing its potential for training robust models on noisy datasets. The official implementation and cell annotations are publicly available at https://github.com/ddrrnn123/CASC-AI.
Chest X-rays (CXRs) play an integral role in driving critical decisions in disease management and patient care. While recent innovations have led to specialized models for various CXR interpretation tasks, these solutions often operate in isolation, limiting their practical utility in clinical practice. We present MedRAX, the first versatile AI agent that seamlessly integrates state-of-the-art CXR analysis tools and multimodal large language models into a unified framework. MedRAX dynamically leverages these models to address complex medical queries without requiring additional training. To rigorously evaluate its capabilities, we introduce ChestAgentBench, a comprehensive benchmark containing 2,500 complex medical queries across 7 diverse categories. Our experiments demonstrate that MedRAX achieves state-of-the-art performance compared to both open-source and proprietary models, representing a significant step toward the practical deployment of automated CXR interpretation systems. Data and code have been publicly available at https://github.com/bowang-lab/MedRAX
Recent LLMs have enabled significant advancements for conversational agents. However, they are also well known to hallucinate, producing responses that seem plausible but are factually incorrect. On the other hand, users tend to over-rely on LLM-based AI agents, accepting AI's suggestion even when it is wrong. Adding positive friction, such as explanations or getting user confirmations, has been proposed as a mitigation in AI-supported decision-making systems. In this paper, we propose an accountability model for LLM-based task-oriented dialogue agents to address user overreliance via friction turns in cases of model uncertainty and errors associated with dialogue state tracking (DST). The accountability model is an augmented LLM with an additional accountability head that functions as a binary classifier to predict the relevant slots of the dialogue state mentioned in the conversation. We perform our experiments with multiple backbone LLMs on two established benchmarks (MultiWOZ and Snips). Our empirical findings demonstrate that the proposed approach not only enables reliable estimation of AI agent errors but also guides the decoder in generating more accurate actions. We observe around 3% absolute improvement in joint goal accuracy (JGA) of DST output by incorporating accountability heads into modern LLMs. Self-correcting the detected errors further increases the JGA from 67.13 to 70.51, achieving state-of-the-art DST performance. Finally, we show that error correction through user confirmations (friction turn) achieves a similar performance gain, highlighting its potential to reduce user overreliance.
AI Agent, powered by large language models (LLMs) as its cognitive core, is an intelligent agentic system capable of autonomously controlling and determining the execution paths under user's instructions. With the burst of capabilities of LLMs and various plugins, such as RAG, text-to-image/video/3D, etc., the potential of AI Agents has been vastly expanded, with their capabilities growing stronger by the day. However, at the intersection between AI and web3, there is currently no ideal agentic framework that can seamlessly integrate web3 applications into AI agent functionalities. In this paper, we propose Eliza, the first open-source web3-friendly Agentic framework that makes the deployment of web3 applications effortless. We emphasize that every aspect of Eliza is a regular Typescript program under the full control of its user, and it seamlessly integrates with web3 (i.e., reading and writing blockchain data, interacting with smart contracts, etc.). Furthermore, we show how stable performance is achieved through the pragmatic implementation of the key components of Eliza's runtime. Our code is publicly available at https://github.com/ai16z/eliza.
With over 85 million CT scans performed annually in the United States, creating tumor-related reports is a challenging and time-consuming task for radiologists. To address this need, we present RadGPT, an Anatomy-Aware Vision-Language AI Agent for generating detailed reports from CT scans. RadGPT first segments tumors, including benign cysts and malignant tumors, and their surrounding anatomical structures, then transforms this information into both structured reports and narrative reports. These reports provide tumor size, shape, location, attenuation, volume, and interactions with surrounding blood vessels and organs. Extensive evaluation on unseen hospitals shows that RadGPT can produce accurate reports, with high sensitivity/specificity for small tumor (<2 cm) detection: 80/73% for liver tumors, 92/78% for kidney tumors, and 77/77% for pancreatic tumors. For large tumors, sensitivity ranges from 89% to 97%. The results significantly surpass the state-of-the-art in abdominal CT report generation. RadGPT generated reports for 17 public datasets. Through radiologist review and refinement, we have ensured the reports' accuracy, and created the first publicly available image-text 3D medical dataset, comprising over 1.8 million text tokens and 2.7 million images from 9,262 CT scans, including 2,947 tumor scans/reports of 8,562 tumor instances. Our reports can: (1) localize tumors in eight liver sub-segments and three pancreatic sub-segments annotated per-voxel; (2) determine pancreatic tumor stage (T1-T4) in 260 reports; and (3) present individual analyses of multiple tumors--rare in human-made reports. Importantly, 948 of the reports are for early-stage tumors.
Minecraft has emerged as a valuable testbed for embodied intelligence and sequential decision-making research, yet the development and validation of novel agents remains hindered by significant engineering challenges. This paper presents MineStudio, an open-source software package designed to streamline embodied policy development in Minecraft. MineStudio represents the first comprehensive integration of seven critical engineering components: simulator, data, model, offline pretraining, online finetuning, inference, and benchmark, thereby allowing users to concentrate their efforts on algorithm innovation. We provide a user-friendly API design accompanied by comprehensive documentation and tutorials. The complete codebase is publicly available at https://github.com/CraftJarvis/MineStudio.
Imagine a world where AI can handle your work while you sleep - organizing your research materials, drafting a report, or creating a presentation you need for tomorrow. However, while current digital agents can perform simple tasks, they are far from capable of handling the complex real-world work that humans routinely perform. We present PC Agent, an AI system that demonstrates a crucial step toward this vision through human cognition transfer. Our key insight is that the path from executing simple "tasks" to handling complex "work" lies in efficiently capturing and learning from human cognitive processes during computer use. To validate this hypothesis, we introduce three key innovations: (1) PC Tracker, a lightweight infrastructure that efficiently collects high-quality human-computer interaction trajectories with complete cognitive context; (2) a two-stage cognition completion pipeline that transforms raw interaction data into rich cognitive trajectories by completing action semantics and thought processes; and (3) a multi-agent system combining a planning agent for decision-making with a grounding agent for robust visual grounding. Our preliminary experiments in PowerPoint presentation creation reveal that complex digital work capabilities can be achieved with a small amount of high-quality cognitive data - PC Agent, trained on just 133 cognitive trajectories, can handle sophisticated work scenarios involving up to 50 steps across multiple applications. This demonstrates the data efficiency of our approach, highlighting that the key to training capable digital agents lies in collecting human cognitive data. By open-sourcing our complete framework, including the data collection infrastructure and cognition completion methods, we aim to lower the barriers for the research community to develop truly capable digital agents.
Despite the rapid advancements in text-to-image (T2I) synthesis, enabling precise visual control remains a significant challenge. Existing works attempted to incorporate multi-facet controls (text and sketch), aiming to enhance the creative control over generated images. However, our pilot study reveals that the expressive power of humans far surpasses the capabilities of current methods. Users desire a more versatile approach that can accommodate their diverse creative intents, ranging from controlling individual subjects to manipulating the entire scene composition. We present VersaGen, a generative AI agent that enables versatile visual control in T2I synthesis. VersaGen admits four types of visual controls: i) single visual subject; ii) multiple visual subjects; iii) scene background; iv) any combination of the three above or merely no control at all. We train an adaptor upon a frozen T2I model to accommodate the visual information into the text-dominated diffusion process. We introduce three optimization strategies during the inference phase of VersaGen to improve generation results and enhance user experience. Comprehensive experiments on COCO and Sketchy validate the effectiveness and flexibility of VersaGen, as evidenced by both qualitative and quantitative results.
다중 모달 대규모 언어 모델(Multimodal Large Language Models, MLLMs)의 비전-언어 이해 능력을 향상시키기 위해 제안된 ZoomEye는 기존의 텍스트 중심 추론 방식의 한계를 극복하는 혁신적인 접근법이다. 기존 MLLMs는 시각적 입력이 고정된 상태에서 텍스트 토큰의 조합을 탐색하는 방식으로, 세밀한 요소가 많은 이미지에서 풍부한 시각 정보를 효과적으로 활용하지 못하는 문제를 안고 있다. 이를 해결하기 위해 ZoomEye는 비전 수준의 추론을 가능하게 하여 모델이 특정 이미지의 특정 영역으로 동적으로 확대하여 필요한 시각적 단서를 수집할 수 있도록 한다.
ZoomEye는 훈련이 필요 없는 모델 독립적인 트리 탐색 알고리즘으로, 이미지를 계층적 트리 구조로 처리한다. 이 구조에서 각 자식 노드는 부모 노드의 확대된 하위 영역을 나타내며, 루트 노드는 전체 이미지를 의미한다. 모델은 루트에서 리프 노드로 탐색하면서 작업에 관련된 시각적 증거를 찾는다. 이러한 방식은 인간이 이미지를 탐색하는 방식과 유사하여, MLLMs의 비전-언어 이해 능력을 크게 향상시킨다.
실험 결과, ZoomEye는 여러 MLLMs의 성능을 유의미하게 개선하는 것으로 나타났다. 예를 들어, InternVL2.5-8B 모델은 HR-Bench에서 15.71% 및 17.69%의 성능 향상을 보였으며, 작은 3-8B MLLMs조차도 강력한 대형 모델인 GPT-4o를 초월하는 성과를 기록하였다. 이러한 결과는 ZoomEye가 MLLMs의 활용 가능성을 넓히고, 다양한 비전-언어 작업에서의 성능을 향상시키는 데 기여할 것임을 시사한다.
ZoomEye의 접근법은 기존의 고정 해상도 방식에서 벗어나, AnyRes라는 방법을 도입하여 원본 이미지를 여러 개의 동일 면적 블록으로 나누고 각 블록을 독립적으로 인코딩하는 방식을 통해 다양한 해상도를 유연하게 처리할 수 있도록 한다. 이로 인해 MLLMs는 더욱 세밀한 시각적 정보를 효과적으로 활용할 수 있게 된다. ZoomEye는 MLLMs의 비전 수준의 추론 능력을 혁신적으로 개선하며, 향후 다양한 비전-언어 작업에서의 응용 가능성을 높이는 중요한 기여를 할 것으로 기대된다.
Frontier AI safety policies highlight automation of AI research and development (R&D) by AI agents as an important capability to anticipate. However, there exist few evaluations for AI R&D capabilities, and none that are highly realistic and have a direct comparison to human performance. We introduce RE-Bench (Research Engineering Benchmark, v1), which consists of 7 challenging, open-ended ML research engineering environments and data from 71 8-hour attempts by 61 distinct human experts. We confirm that our experts make progress in the environments given 8 hours, with 82% of expert attempts achieving a non-zero score and 24% matching or exceeding our strong reference solutions. We compare humans to several public frontier models through best-of-k with varying time budgets and agent designs, and find that the best AI agents achieve a score 4x higher than human experts when both are given a total time budget of 2 hours per environment. However, humans currently display better returns to increasing time budgets, narrowly exceeding the top AI agent scores given an 8-hour budget, and achieving 2x the score of the top AI agent when both are given 32 total hours (across different attempts). Qualitatively, we find that modern AI agents possess significant expertise in many ML topics -- e.g. an agent wrote a faster custom Triton kernel than any of our human experts' -- and can generate and test solutions over ten times faster than humans, at much lower cost. We open-source the evaluation environments, human expert data, analysis code and agent trajectories to facilitate future research.
As financial markets grow increasingly complex, there is a rising need for automated tools that can effectively assist human analysts in equity research, particularly within sell-side research. While Generative AI (GenAI) has attracted significant attention in this field, existing AI solutions often fall short due to their narrow focus on technical factors and limited capacity for discretionary judgment. These limitations hinder their ability to adapt to new data in real-time and accurately assess risks, which diminishes their practical value for investors. This paper presents FinRobot, the first AI agent framework specifically designed for equity research. FinRobot employs a multi-agent Chain of Thought (CoT) system, integrating both quantitative and qualitative analyses to emulate the comprehensive reasoning of a human analyst. The system is structured around three specialized agents: the Data-CoT Agent, which aggregates diverse data sources for robust financial integration; the Concept-CoT Agent, which mimics an analysts reasoning to generate actionable insights; and the Thesis-CoT Agent, which synthesizes these insights into a coherent investment thesis and report. FinRobot provides thorough company analysis supported by precise numerical data, industry-appropriate valuation metrics, and realistic risk assessments. Its dynamically updatable data pipeline ensures that research remains timely and relevant, adapting seamlessly to new financial information. Unlike existing automated research tools, such as CapitalCube and Wright Reports, FinRobot delivers insights comparable to those produced by major brokerage firms and fundamental research vendors. We open-source FinRobot at \url{https://github. com/AI4Finance-Foundation/FinRobot}.
In recent years, the application of generative artificial intelligence (GenAI) in financial analysis and investment decision-making has gained significant attention. However, most existing approaches rely on single-agent systems, which fail to fully utilize the collaborative potential of multiple AI agents. In this paper, we propose a novel multi-agent collaboration system designed to enhance decision-making in financial investment research. The system incorporates agent groups with both configurable group sizes and collaboration structures to leverage the strengths of each agent group type. By utilizing a sub-optimal combination strategy, the system dynamically adapts to varying market conditions and investment scenarios, optimizing performance across different tasks. We focus on three sub-tasks: fundamentals, market sentiment, and risk analysis, by analyzing the 2023 SEC 10-K forms of 30 companies listed on the Dow Jones Index. Our findings reveal significant performance variations based on the configurations of AI agents for different tasks. The results demonstrate that our multi-agent collaboration system outperforms traditional single-agent models, offering improved accuracy, efficiency, and adaptability in complex financial environments. This study highlights the potential of multi-agent systems in transforming financial analysis and investment decision-making by integrating diverse analytical perspectives.
Smartphone agents are increasingly important for helping users control devices efficiently, with (Multimodal) Large Language Model (MLLM)-based approaches emerging as key contenders. Fairly comparing these agents is essential but challenging, requiring a varied task scope, the integration of agents with different implementations, and a generalisable evaluation pipeline to assess their strengths and weaknesses. In this paper, we present SPA-Bench, a comprehensive SmartPhone Agent Benchmark designed to evaluate (M)LLM-based agents in an interactive environment that simulates real-world conditions. SPA-Bench offers three key contributions: (1) A diverse set of tasks covering system and third-party apps in both English and Chinese, focusing on features commonly used in daily routines; (2) A plug-and-play framework enabling real-time agent interaction with Android devices, integrating over ten agents with the flexibility to add more; (3) A novel evaluation pipeline that automatically assesses agent performance across multiple dimensions, encompassing seven metrics related to task completion and resource consumption. Our extensive experiments across tasks and agents reveal challenges like interpreting mobile user interfaces, action grounding, memory retention, and execution costs. We propose future research directions to ease these difficulties, moving closer to real-world smartphone agent applications. SPA-Bench is available at https://ai-agents-2030.github.io/SPA-Bench/.
We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI), aimed at transforming human-computer interaction by automating complex, multi-step tasks. Agent S aims to address three key challenges in automating computer tasks: acquiring domain-specific knowledge, planning over long task horizons, and handling dynamic, non-uniform interfaces. To this end, Agent S introduces experience-augmented hierarchical planning, which learns from external knowledge search and internal experience retrieval at multiple levels, facilitating efficient task planning and subtask execution. In addition, it employs an Agent-Computer Interface (ACI) to better elicit the reasoning and control capabilities of GUI agents based on Multimodal Large Language Models (MLLMs). Evaluation on the OSWorld benchmark shows that Agent S outperforms the baseline by 9.37% on success rate (an 83.6% relative improvement) and achieves a new state-of-the-art. Comprehensive analysis highlights the effectiveness of individual components and provides insights for future improvements. Furthermore, Agent S demonstrates broad generalizability to different operating systems on a newly-released WindowsAgentArena benchmark. Code available at https://github.com/simular-ai/Agent-S.
Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In contrast, humans can flexibly solve complex tasks by learning reusable task workflows from past experiences and using them to guide future actions. To build agents that can similarly benefit from this process, we introduce Agent Workflow Memory (AWM), a method for inducing commonly reused routines, i.e., workflows, and selectively providing workflows to the agent to guide subsequent generations. AWM flexibly applies to both offline and online scenarios, where agents induce workflows from training examples beforehand or from test queries on the fly. We experiment on two major web navigation benchmarks -- Mind2Web and WebArena -- that collectively cover 1000+ tasks from 200+ domains across travel, shopping, and social media, among others. AWM substantially improves the baseline results by 24.6% and 51.1% relative success rate on Mind2Web and WebArena while reducing the number of steps taken to solve WebArena tasks successfully. Furthermore, online AWM robustly generalizes in cross-task, website, and domain evaluations, surpassing baselines from 8.9 to 14.0 absolute points as train-test task distribution gaps widen.
A key challenge in artificial intelligence is the creation of systems capable of autonomously advancing scientific understanding by exploring novel domains, identifying complex patterns, and uncovering previously unseen connections in vast scientific data. In this work, we present SciAgents, an approach that leverages three core concepts: (1) the use of large-scale ontological knowledge graphs to organize and interconnect diverse scientific concepts, (2) a suite of large language models (LLMs) and data retrieval tools, and (3) multi-agent systems with in-situ learning capabilities. Applied to biologically inspired materials, SciAgents reveals hidden interdisciplinary relationships that were previously considered unrelated, achieving a scale, precision, and exploratory power that surpasses traditional human-driven research methods. The framework autonomously generates and refines research hypotheses, elucidating underlying mechanisms, design principles, and unexpected material properties. By integrating these capabilities in a modular fashion, the intelligent system yields material discoveries, critique and improve existing hypotheses, retrieve up-to-date data about existing research, and highlights their strengths and limitations. Our case studies demonstrate scalable capabilities to combine generative AI, ontological representations, and multi-agent modeling, harnessing a `swarm of intelligence' similar to biological systems. This provides new avenues for materials discovery and accelerates the development of advanced materials by unlocking Nature's design principles.
Autonomous agents powered by large language models (LLMs) have attracted significant research interest. However, the open-source community faces many challenges in developing specialized models for agent tasks, driven by the scarcity of high-quality agent datasets and the absence of standard protocols in this area. We introduce and publicly release xLAM, a series of large action models designed for AI agent tasks. The xLAM series includes five models with both dense and mixture-of-expert architectures, ranging from 1B to 8x22B parameters, trained using a scalable, flexible pipeline that unifies, augments, and synthesizes diverse datasets to enhance AI agents' generalizability and performance across varied environments. Our experimental results demonstrate that xLAM consistently delivers exceptional performance across multiple agent ability benchmarks, notably securing the 1st position on the Berkeley Function-Calling Leaderboard, outperforming GPT-4, Claude-3, and many other models in terms of tool use. By releasing the xLAM series, we aim to advance the performance of open-source LLMs for autonomous AI agents, potentially accelerating progress and democratizing access to high-performance models for agent tasks. Models are available at https://huggingface.co/collections/Salesforce/xlam-models-65f00e2a0a63bbcd1c2dade4