Augmenting large language models (LLMs) with browsing tools substantially improves their potential as deep search agents to solve complex, real-world tasks. Yet, open LLMs still perform poorly in such settings due to limited long-horizon reasoning capacity with browsing tools and the lack of sufficiently difficult supervised data. To address these challenges, we present DeepDive to advance deep search agents. First, we propose a strategy to automatically synthesize complex, difficult, and hard-to-find questions from open knowledge graphs. Second, we apply end-to-end multi-turn reinforcement learning (RL) to enhance LLMs' long-horizon reasoning with deep search. Experiments show that DeepDive-32B achieves a new open-source competitive result on BrowseComp, outperforming WebSailor, DeepSeek-R1-Browse, and Search-o1. We demonstrate that multi-turn RL training improves deep search ability and significantly contributes to the performance improvements across multiple benchmarks. We observe that DeepDive enables test-time scaling of tool calls and parallel sampling. All datasets, models, and code are publicly available at https://github.com/THUDM/DeepDive.
To optimize the reasoning and problem-solving capabilities of Large Language Models (LLMs), we propose a novel cloud-edge collaborative architecture that enables a structured, multi-agent prompting framework. This framework comprises three specialized components: GuideLLM, a lightweight model deployed at the edge to provide methodological guidance; SolverLLM, a more powerful model hosted in the cloud responsible for generating code solutions; and JudgeLLM, an automated evaluator for assessing solution correctness and quality. To evaluate and demonstrate the effectiveness of this architecture in realistic settings, we introduce RefactorCoderQA, a comprehensive benchmark designed to evaluate and enhance the performance of Large Language Models (LLMs) across multi-domain coding tasks. Motivated by the limitations of existing benchmarks, RefactorCoderQA systematically covers various technical domains, including Software Engineering, Data Science, Machine Learning, and Natural Language Processing, using authentic coding challenges from Stack Overflow. Extensive experiments reveal that our fine-tuned model, RefactorCoder-MoE, achieves state-of-the-art performance, significantly outperforming leading open-source and commercial baselines with an overall accuracy of 76.84%. Human evaluations further validate the interpretability, accuracy, and practical relevance of the generated solutions. In addition, we evaluate system-level metrics, such as throughput and latency, to gain deeper insights into the performance characteristics and trade-offs of the proposed architecture.
We present RecoWorld, a blueprint for building simulated environments tailored to agentic recommender systems. Such environments give agents a proper training space where they can learn from errors without impacting real users. RecoWorld distinguishes itself with a dual-view architecture: a simulated user and an agentic recommender engage in multi-turn interactions aimed at maximizing user retention. The user simulator reviews recommended items, updates its mindset, and when sensing potential user disengagement, generates reflective instructions. The agentic recommender adapts its recommendations by incorporating these user instructions and reasoning traces, creating a dynamic feedback loop that actively engages users. This process leverages the exceptional reasoning capabilities of modern LLMs. We explore diverse content representations within the simulator, including text-based, multimodal, and semantic ID modeling, and discuss how multi-turn RL enables the recommender to refine its strategies through iterative interactions. RecoWorld also supports multi-agent simulations, allowing creators to simulate the responses of targeted user populations. It marks an important first step toward recommender systems where users and agents collaboratively shape personalized information streams. We envision new interaction paradigms where "user instructs, recommender responds," jointly optimizing user retention and engagement.
The work describes the development of a hybrid control architecture for an anthropomorphic tour guide robot, combining a multi-agent resource management system with automatic behavior scenario generation based on large language models. The proposed approach aims to overcome the limitations of traditional systems, which rely on manual tuning of behavior scenarios. These limitations include manual configuration, low flexibility, and lack of naturalness in robot behavior. The process of preparing tour scenarios is implemented through a two-stage generation: first, a stylized narrative is created, then non-verbal action tags are integrated into the text. The multi-agent system ensures coordination and conflict resolution during the execution of parallel actions, as well as maintaining default behavior after the completion of main operations, contributing to more natural robot behavior. The results obtained from the trial demonstrate the potential of the proposed approach for automating and scaling social robot control systems.
A common assumption holds that scaling data and parameters yields increasingly structured, generalisable internal representations. We interrogate this assumption in clinical natural language inference (NLI) by adopting a benchmark decomposed into four reasoning families, Causal Attribution, Compositional Grounding, Epistemic Verification, and Risk State Abstraction, and introducing CARENLI, a Compartmentalised Agentic Reasoning for Clinical NLI that separates knowledge access from principled inference. CARENLI routes each premise, statement pair to a family specific solver and enforces auditable procedures via a planner, verifier, and refiner. Across four LLMs, CARENLI improves fidelity by up to 42 points, reaching 98.0% in Causal Attribution and 81.2% in Risk State Abstraction. Verifiers flag violations with near-ceiling reliability, while refiners correct a substantial share of epistemic errors. Remaining failures cluster in routing, identifying family classification as the main bottleneck. These results show that LLMs often retain relevant facts but default to heuristics when inference is underspecified, a dissociation CARENLI makes explicit while offering a framework for safer, auditable reasoning.
Automated characterization of porous materials has the potential to accelerate materials discovery, but it remains limited by the complexity of simulation setup and force field selection. We propose a multi-agent framework in which LLM-based agents can autonomously understand a characterization task, plan appropriate simulations, assemble relevant force fields, execute them and interpret their results to guide subsequent steps. As a first step toward this vision, we present a multi-agent system for literature-informed force field extraction and automated RASPA simulation setup. Initial evaluations demonstrate high correctness and reproducibility, highlighting this approach's potential to enable fully autonomous, scalable materials characterization.
Recent advances in large language models (LLMs) have enabled human-like social simulations at unprecedented scale and fidelity, offering new opportunities for computational social science. A key challenge, however, is the construction of persona sets that authentically represent the diversity and distribution of real-world populations. Most existing LLM-based social simulation studies focus primarily on designing agentic frameworks and simulation environments, often overlooking the complexities of persona generation and the potential biases introduced by unrepresentative persona sets. In this paper, we propose a systematic framework for synthesizing high-quality, population-aligned persona sets for LLM-driven social simulation. Our approach begins by leveraging LLMs to generate narrative personas from long-term social media data, followed by rigorous quality assessment to filter out low-fidelity profiles. We then apply importance sampling to achieve global alignment with reference psychometric distributions, such as the Big Five personality traits. To address the needs of specific simulation contexts, we further introduce a task-specific module that adapts the globally aligned persona set to targeted subpopulations. Extensive experiments demonstrate that our method significantly reduces population-level bias and enables accurate, flexible social simulation for a wide range of research and policy applications.
The rapid advancement of Large Language Models (LLMs) has significantly enhanced the capabilities of Multi-Agent Systems (MAS) in supporting humans with complex, real-world tasks. However, MAS still face challenges in effective task planning when handling highly complex tasks with uncertainty, often resulting in misleading or incorrect outputs that hinder task execution. To address this, we propose XAgents, a unified multi-agent cooperative framework built on a multipolar task processing graph and IF-THEN rules. XAgents uses the multipolar task processing graph to enable dynamic task planning and handle task uncertainty. During subtask processing, it integrates domain-specific IF-THEN rules to constrain agent behaviors, while global rules enhance inter-agent collaboration. We evaluate the performance of XAgents across three distinct datasets, demonstrating that it consistently surpasses state-of-the-art single-agent and multi-agent approaches in both knowledge-typed and logic-typed question-answering tasks. The codes for XAgents are available at: https://github.com/AGI-FHBC/XAgents.
With the rapid advancement of Large Language Model (LLM), LLM-based agents exhibit exceptional abilities in understanding and generating natural language, facilitating human-like collaboration and information transmission in LLM-based Multi-Agent System (MAS). High-performance LLMs are often hosted on remote servers in public spaces. When tasks involve privacy data, MAS cannot securely utilize these LLMs without implementing privacy-preserving mechanisms. To address this challenge, we propose a General Anonymizing Multi-Agent system (GAMA), which divides the agents' workspace into private and public spaces and protects privacy through the anonymizing mechanism. In the private space, agents handle sensitive data, while in the public space, only anonymized data is utilized. GAMA incorporates two key modules to mitigate semantic loss caused by anonymization: Domain-Rule-based Knowledge Enhancement (DRKE) and Disproof-based Logic Enhancement (DLE). We evaluate GAMA on two public question-answering datasets: Trivia Creative Writing and Logic Grid Puzzle. The results demonstrate that GAMA has superior performance compared to the state-of-the-art models. To further assess its privacy-preserving capabilities, we designed two new datasets: Knowledge Privacy Preservation and Logic Privacy Preservation. The final results highlight GAMA's exceptional effectiveness in both task processing and privacy preservation.
Recent advances in Large Language Models (LLMs) have demonstrated impressive capabilities in financial reasoning and market understanding. Multi-agent LLM frameworks such as TradingAgent and FINMEM augment these models to long-horizon investment tasks, leveraging fundamental and sentiment-based inputs for strategic decision-making. However, such systems are ill-suited for the high-speed, precision-critical demands of High-Frequency Trading (HFT). HFT requires rapid, risk-aware decisions based on structured, short-horizon signals, including technical indicators, chart patterns, and trend-based features, distinct from the long-term semantic reasoning typical of traditional financial LLM applications. To this end, we introduce QuantAgent, the first multi-agent LLM framework explicitly designed for high-frequency algorithmic trading. The system decomposes trading into four specialized agents, Indicator, Pattern, Trend, and Risk, each equipped with domain-specific tools and structured reasoning capabilities to capture distinct aspects of market dynamics over short temporal windows. In zero-shot evaluations across ten financial instruments, including Bitcoin and Nasdaq futures, QuantAgent demonstrates superior performance in both predictive accuracy and cumulative return over 4-hour trading intervals, outperforming strong neural and rule-based baselines. Our findings suggest that combining structured financial priors with language-native reasoning unlocks new potential for traceable, real-time decision systems in high-frequency financial markets.
Large Language Models (LLMs) show promise in generating firmware for embedded systems, but often introduce security flaws and fail to meet real-time performance constraints. This paper proposes a three-phase methodology that combines LLM-based firmware generation with automated security validation and iterative refinement in a virtualized environment. Using structured prompts, models like GPT-4 generate firmware for networking and control tasks, deployed on FreeRTOS via QEMU. These implementations are tested using fuzzing, static analysis, and runtime monitoring to detect vulnerabilities such as buffer overflows (CWE-120), race conditions (CWE-362), and denial-of-service threats (CWE-400). Specialized AI agents for Threat Detection, Performance Optimization, and Compliance Verification collaborate to improve detection and remediation. Identified issues are categorized using CWE, then used to prompt targeted LLM-generated patches in an iterative loop. Experiments show a 92.4\% Vulnerability Remediation Rate (37.3\% improvement), 95.8\% Threat Model Compliance, and 0.87 Security Coverage Index. Real-time metrics include 8.6ms worst-case execution time and 195{\mu}s jitter. This process enhances firmware security and performance while contributing an open-source dataset for future research.
Recent work in scientific machine learning aims to tackle scientific tasks directly by predicting target values with neural networks (e.g., physics-informed neural networks, neural ODEs, neural operators, etc.), but attaining high accuracy and robustness has been challenging. We explore an alternative view: use LLMs to write code that leverages decades of numerical algorithms. This shifts the burden from learning a solution function to making domain-aware numerical choices. We ask whether LLMs can act as SciML agents that, given a natural-language ODE description, generate runnable code that is scientifically appropriate, selecting suitable solvers (stiff vs. non-stiff), and enforcing stability checks. There is currently no benchmark to measure this kind of capability for scientific computing tasks. As such, we first introduce two new datasets: a diagnostic dataset of adversarial "misleading" problems; and a large-scale benchmark of 1,000 diverse ODE tasks. The diagnostic set contains problems whose superficial appearance suggests stiffness, and that require algebraic simplification to demonstrate non-stiffness; and the large-scale benchmark spans stiff and non-stiff ODE regimes. We evaluate open- and closed-source LLM models along two axes: (i) unguided versus guided prompting with domain-specific knowledge; and (ii) off-the-shelf versus fine-tuned variants. Our evaluation measures both executability and numerical validity against reference solutions. We find that with sufficient context and guided prompts, newer instruction-following models achieve high accuracy on both criteria. In many cases, recent open-source systems perform strongly without fine-tuning, while older or smaller models still benefit from fine-tuning. Overall, our preliminary results indicate that careful prompting and fine-tuning can yield a specialized LLM agent capable of reliably solving simple ODE problems.
Key global challenges of our times are characterized by complex interdependencies and can only be effectively addressed through an integrated, participatory effort. Conventional risk analysis frameworks often reduce complexity to ensure manageability, creating silos that hinder comprehensive solutions. A fundamental shift towards holistic strategies is essential to enable effective negotiations between different sectors and to balance the competing interests of stakeholders. However, achieving this balance is often hindered by limited time, vast amounts of information, and the complexity of integrating diverse perspectives. This study presents an AI-assisted negotiation framework that incorporates large language models (LLMs) and AI-based autonomous agents into a negotiation-centered risk analysis workflow. The framework enables stakeholders to simulate negotiations, systematically model dynamics, anticipate compromises, and evaluate solution impacts. By leveraging LLMs' semantic analysis capabilities we could mitigate information overload and augment decision-making process under time constraints. Proof-of-concept implementations were conducted in two real-world scenarios: (i) prudent use of a biopesticide, and (ii) targeted wild animal population control. Our work demonstrates the potential of AI-assisted negotiation to address the current lack of tools for cross-sectoral engagement. Importantly, the solution's open source, web based design, suits for application by a broader audience with limited resources and enables users to tailor and develop it for their own needs.
Large language models (LLMs) enable conversational agents (CAs) to express distinctive personalities, raising new questions about how such designs shape user perceptions. This study investigates how personality expression levels and user-agent personality alignment influence perceptions in goal-oriented tasks. In a between-subjects experiment (N=150), participants completed travel planning with CAs exhibiting low, medium, or high expression across the Big Five traits, controlled via our novel Trait Modulation Keys framework. Results revealed an inverted-U relationship: medium expression produced the most positive evaluations across Intelligence, Enjoyment, Anthropomorphism, Intention to Adopt, Trust, and Likeability, significantly outperforming both extremes. Personality alignment further enhanced outcomes, with Extraversion and Emotional Stability emerging as the most influential traits. Cluster analysis identified three distinct compatibility profiles, with "Well-Aligned" users reporting substantially positive perceptions. These findings demonstrate that personality expression and strategic trait alignment constitute optimal design targets for CA personality, offering design implications as LLM-based CAs become increasingly prevalent.
LLMs promise to assist humans -- not just by answering questions, but by offering useful guidance across a wide range of tasks. But how far does that assistance go? Can a large language model based agent actually help someone accomplish their goal as an active participant? We test this question by engaging an LLM in UNO, a turn-based card game, asking it not to win but instead help another player to do so. We built a tool that allows decoder-only LLMs to participate as agents within the RLCard game environment. These models receive full game-state information and respond using simple text prompts under two distinct prompting strategies. We evaluate models ranging from small (1B parameters) to large (70B parameters) and explore how model scale impacts performance. We find that while all models were able to successfully outperform a random baseline when playing UNO, few were able to significantly aid another player.
Inference-time scaling has emerged as a powerful way to improve large language model (LLM) performance by generating multiple candidate responses and selecting among them. However, existing work on dynamic allocation for test-time compute typically considers only parallel generation methods such as best-of-N, overlooking incremental decoding methods like beam search, and has largely ignored latency, focusing only on token usage. We formulate inference-time scaling as a problem of dynamic compute allocation and method selection, where the system must decide which strategy to apply and how much compute to allocate on a per-query basis. Our framework explicitly incorporates both token cost and wall-clock latency, the latter being critical for user experience and particularly for agentic workflows where models must issue multiple queries efficiently. Experiments on reasoning benchmarks show that our approach consistently outperforms static strategies, achieving favorable accuracy-cost trade-offs while remaining practical for deployment.
The advancement of large language models (LLMs) and code agents has demonstrated significant potential to assist software engineering (SWE) tasks, such as autonomous issue resolution and feature addition. Existing AI for software engineering leaderboards (e.g., SWE-bench) focus solely on solution accuracy, ignoring the crucial factor of effectiveness in a resource-constrained world. This is a universal problem that also exists beyond software engineering tasks: any AI system should be more than correct - it must also be cost-effective. To address this gap, we introduce SWE-Effi, a set of new metrics to re-evaluate AI systems in terms of holistic effectiveness scores. We define effectiveness as the balance between the accuracy of outcome (e.g., issue resolve rate) and the resources consumed (e.g., token and time). In this paper, we specifically focus on the software engineering scenario by re-ranking popular AI systems for issue resolution on a subset of the SWE-bench benchmark using our new multi-dimensional metrics. We found that AI system's effectiveness depends not just on the scaffold itself, but on how well it integrates with the base model, which is key to achieving strong performance in a resource-efficient manner. We also identified systematic challenges such as the "token snowball" effect and, more significantly, a pattern of "expensive failures". In these cases, agents consume excessive resources while stuck on unsolvable tasks - an issue that not only limits practical deployment but also drives up the cost of failed rollouts during RL training. Lastly, we observed a clear trade-off between effectiveness under the token budget and effectiveness under the time budget, which plays a crucial role in managing project budgets and enabling scalable reinforcement learning, where fast responses are essential.
Does continued scaling of large language models (LLMs) yield diminishing returns? Real-world value often stems from the length of task an agent can complete. We start this work by observing the simple but counterintuitive fact that marginal gains in single-step accuracy can compound into exponential improvements in the length of a task a model can successfully complete. Then, we argue that failures of LLMs when simple tasks are made longer arise from mistakes in execution, rather than an inability to reason. We propose isolating execution capability, by explicitly providing the knowledge and plan needed to solve a long-horizon task. We find that larger models can correctly execute significantly more turns even when small models have 100\% single-turn accuracy. We observe that the per-step accuracy of models degrades as the number of steps increases. This is not just due to long-context limitations -- curiously, we observe a self-conditioning effect -- models become more likely to make mistakes when the context contains their errors from prior turns. Self-conditioning does not reduce by just scaling the model size. In contrast, recent thinking models do not self-condition, and can also execute much longer tasks in a single turn. We conclude by benchmarking frontier thinking models on the length of task they can execute in a single turn. Overall, by focusing on the ability to execute, we hope to reconcile debates on how LLMs can solve complex reasoning problems yet fail at simple tasks when made longer, and highlight the massive benefits of scaling model size and sequential test-time compute for long-horizon tasks.
The advancement of large language models (LLMs) has enabled the construction of multi-agent systems to solve complex tasks by dividing responsibilities among specialized agents, such as a planning agent for subgoal generation and a grounding agent for executing tool-use actions. Most existing methods typically fine-tune these agents independently, leading to capability gaps among them with poor coordination. To address this, we propose MOAT, a Multi-Agent Joint Alignment Tuning framework that improves agents collaboration through iterative alignment. MOAT alternates between two key stages: (1) Planning Agent Alignment, which optimizes the planning agent to generate subgoal sequences that better guide the grounding agent; and (2) Grounding Agent Improving, which fine-tunes the grounding agent using diverse subgoal-action pairs generated by the agent itself to enhance its generalization capablity. Theoretical analysis proves that MOAT ensures a non-decreasing and progressively convergent training process. Experiments across six benchmarks demonstrate that MOAT outperforms state-of-the-art baselines, achieving average improvements of 3.1% on held-in tasks and 4.4% on held-out tasks.
Serverless computing provides dynamic scalability, but its infrastructure overhead becomes a bottleneck for emerging workloads such as LLM agents, which exhibit unpredictable invocation patterns and variable resource demands. Our analysis shows that for these agents, the cost of running on serverless platforms can reach up to 70% of the cost of LLM API calls. This finding motivates the need for a more efficient, high-density serverless platform. We present TrEnv, a co-designed serverless platform that supports both container- and VM-based environments, optimized for the unique demands of LLM agents. TrEnv reduces startup latency and memory usage through repurposable sandboxes and memory templates, which enable fast reuse and restoration of execution environments. To further reduce overhead in VM-based agent workloads, TrEnv leverages browser sharing and a page cache bypassing mechanism. Evaluations show that TrEnv reduces P99 latency by up to 7X and memory usage by 48% in container-based settings, and achieves up to 58% lower P99 latency and 61% memory savings for VM-based agents compared to state-of-the-art systems like E2B.
LLMs now form the backbone of AI agents for a diverse array of applications, including tool use, command-line agents, and web or computer use agents. These agentic LLM inference tasks are fundamentally different from chatbot-focused inference -- they often have much larger context lengths to capture complex, prolonged inputs, such as entire webpage DOMs or complicated tool call trajectories. This, in turn, generates significant off-chip memory traffic for the underlying hardware at the inference stage and causes the workload to be constrained by two memory walls, namely the bandwidth and capacity memory walls, preventing the on-chip compute units from achieving high utilization. In this paper, we introduce PLENA, a hardware-software co-designed system that applies three core optimization pathways to tackle these challenges. PLENA includes an efficient hardware implementation of compute and memory units supporting an asymmetric quantization scheme. PLENA also features a novel flattened systolic array architecture that has native support for FlashAttention to tackle these memory walls in the scenario of inference serving for long-context LLMs. Additionally, PLENA is developed with a complete stack, including a custom ISA, a compiler, a cycle-emulated simulator, and an automated design space exploration flow. The simulated results show that PLENA achieves up to 8.5x higher utilization than existing accelerators, and delivers 2.24x higher throughput than the A100 GPU and 3.85x higher throughput than the TPU v6e, under the same multiplier count and memory settings. The full PLENA system will also be open-sourced.
Predicting cryptocurrency returns is notoriously difficult: price movements are driven by a fast-shifting blend of on-chain activity, news flow, and social sentiment, while labeled training data are scarce and expensive. In this paper, we present Meta-RL-Crypto, a unified transformer-based architecture that unifies meta-learning and reinforcement learning (RL) to create a fully self-improving trading agent. Starting from a vanilla instruction-tuned LLM, the agent iteratively alternates between three roles-actor, judge, and meta-judge-in a closed-loop architecture. This learning process requires no additional human supervision. It can leverage multimodal market inputs and internal preference feedback. The agent in the system continuously refines both the trading policy and evaluation criteria. Experiments across diverse market regimes demonstrate that Meta-RL-Crypto shows good performance on the technical indicators of the real market and outperforming other LLM-based baselines.
Large Language Models (LLMs) are increasingly deployed in enterprise applications, yet their reliability remains limited by hallucinations, i.e., confident but factually incorrect information. Existing detection approaches, such as SelfCheckGPT and MetaQA, primarily target standalone LLMs and do not address the unique challenges of Retrieval-Augmented Generation (RAG) systems, where responses must be consistent with retrieved evidence. We therefore present MetaRAG, a metamorphic testing framework for hallucination detection in Retrieval-Augmented Generation (RAG) systems. MetaRAG operates in a real-time, unsupervised, black-box setting, requiring neither ground-truth references nor access to model internals, making it suitable for proprietary and high-stakes domains. The framework proceeds in four stages: (1) decompose answers into atomic factoids, (2) generate controlled mutations of each factoid using synonym and antonym substitutions, (3) verify each variant against the retrieved context (synonyms are expected to be entailed and antonyms contradicted), and (4) aggregate penalties for inconsistencies into a response-level hallucination score. Crucially for identity-aware AI, MetaRAG localizes unsupported claims at the factoid span where they occur (e.g., pregnancy-specific precautions, LGBTQ+ refugee rights, or labor eligibility), allowing users to see flagged spans and enabling system designers to configure thresholds and guardrails for identity-sensitive queries. Experiments on a proprietary enterprise dataset illustrate the effectiveness of MetaRAG for detecting hallucinations and enabling trustworthy deployment of RAG-based conversational agents. We also outline a topic-based deployment design that translates MetaRAG's span-level scores into identity-aware safeguards; this design is discussed but not evaluated in our experiments.
Recent advances in large language models (LLMs) have enabled the emergence of general-purpose agents for automating end-to-end machine learning (ML) workflows, including data analysis, feature engineering, model training, and competition solving. However, existing benchmarks remain limited in task coverage, domain diversity, difficulty modeling, and evaluation rigor, failing to capture the full capabilities of such agents in realistic settings. We present TAM Bench, a diverse, realistic, and structured benchmark for evaluating LLM-based agents on end-to-end ML tasks. TAM Bench features three key innovations: (1) A browser automation and LLM-based task acquisition system that automatically collects and structures ML challenges from platforms such as Kaggle, AIcrowd, and Biendata, spanning multiple task types and data modalities (e.g., tabular, text, image, graph, audio); (2) A leaderboard-driven difficulty modeling mechanism that estimates task complexity using participant counts and score dispersion, enabling scalable and objective task calibration; (3) A multi-dimensional evaluation framework incorporating performance, format compliance, constraint adherence, and task generalization. Based on 150 curated AutoML tasks, we construct three benchmark subsets of different sizes -- Lite, Medium, and Full -- designed for varying evaluation scenarios. The Lite version, with 18 tasks and balanced coverage across modalities and difficulty levels, serves as a practical testbed for daily benchmarking and comparative studies.
Materials characterization is fundamental to acquiring materials information, revealing the processing-microstructure-property relationships that guide material design and optimization. While multimodal large language models (MLLMs) have recently shown promise in generative and predictive tasks within materials science, their capacity to understand real-world characterization imaging data remains underexplored. To bridge this gap, we present MatCha, the first benchmark for materials characterization image understanding, comprising 1,500 questions that demand expert-level domain expertise. MatCha encompasses four key stages of materials research comprising 21 distinct tasks, each designed to reflect authentic challenges faced by materials scientists. Our evaluation of state-of-the-art MLLMs on MatCha reveals a significant performance gap compared to human experts. These models exhibit degradation when addressing questions requiring higher-level expertise and sophisticated visual perception. Simple few-shot and chain-of-thought prompting struggle to alleviate these limitations. These findings highlight that existing MLLMs still exhibit limited adaptability to real-world materials characterization scenarios. We hope MatCha will facilitate future research in areas such as new material discovery and autonomous scientific agents. MatCha is available at https://github.com/FreedomIntelligence/MatCha.
With the rapid advancement of large language models (LLMs), Multi-agent Systems (MAS) have achieved significant progress in various application scenarios. However, substantial challenges remain in designing versatile, robust, and efficient platforms for agent deployment. To address these limitations, we propose \textbf{LightAgent}, a lightweight yet powerful agentic framework, effectively resolving the trade-off between flexibility and simplicity found in existing frameworks. LightAgent integrates core functionalities such as Memory (mem0), Tools, and Tree of Thought (ToT), while maintaining an extremely lightweight structure. As a fully open-source solution, it seamlessly integrates with mainstream chat platforms, enabling developers to easily build self-learning agents. We have released LightAgent at \href{https://github.com/wxai-space/LightAgent}{https://github.com/wxai-space/LightAgent}
In long-horizon tasks, recent agents based on Large Language Models (LLMs) face a significant challenge that sparse, outcome-based rewards make it difficult to assign credit to intermediate steps. Previous methods mainly focus on creating dense reward signals to guide learning, either through traditional reinforcement learning techniques like inverse reinforcement learning or by using Process Reward Models for step-by-step feedback. In this paper, we identify a fundamental problem in the learning dynamics of LLMs: the magnitude of policy gradients is inherently coupled with the entropy, which leads to inefficient small updates for confident correct actions and potentially destabilizes large updates for uncertain ones. To resolve this, we propose Entropy-Modulated Policy Gradients (EMPG), a framework that re-calibrates the learning signal based on step-wise uncertainty and the final task outcome. EMPG amplifies updates for confident correct actions, penalizes confident errors, and attenuates updates from uncertain steps to stabilize exploration. We further introduce a bonus term for future clarity that encourages agents to find more predictable solution paths. Through comprehensive experiments on three challenging agent tasks, WebShop, ALFWorld, and Deep Search, we demonstrate that EMPG achieves substantial performance gains and significantly outperforms strong policy gradient baselines. Project page is at https://empgseed-seed.github.io/
Large language models (LLMs) have shown great promise in automating data science workflows, but existing models still struggle with multi-step reasoning and tool use, which limits their effectiveness on complex data analysis tasks. To address this, we propose a scalable pipeline that extracts high-quality, tool-based data analysis tasks and their executable multi-step solutions from real-world Jupyter notebooks and associated data files. Using this pipeline, we introduce NbQA, a large-scale dataset of standardized task-solution pairs that reflect authentic tool-use patterns in practical data science scenarios. To further enhance multi-step reasoning, we present Jupiter, a framework that formulates data analysis as a search problem and applies Monte Carlo Tree Search (MCTS) to generate diverse solution trajectories for value model learning. During inference, Jupiter combines the value model and node visit counts to efficiently collect executable multi-step plans with minimal search steps. Experimental results show that Qwen2.5-7B and 14B-Instruct models on NbQA solve 77.82% and 86.38% of tasks on InfiAgent-DABench, respectively-matching or surpassing GPT-4o and advanced agent frameworks. Further evaluations demonstrate improved generalization and stronger tool-use reasoning across diverse multi-step reasoning tasks.
Question Answering over Tabular Data (Table QA) presents unique challenges due to the diverse structure, size, and data types of real-world tables. The SemEval 2025 Task 8 (DataBench) introduced a benchmark composed of large-scale, domain-diverse datasets to evaluate the ability of models to accurately answer structured queries. We propose a Natural Language to SQL (NL-to-SQL) approach leveraging large language models (LLMs) such as GPT-4o, GPT-4o-mini, and DeepSeek v2:16b to generate SQL queries dynamically. Our system follows a multi-stage pipeline involving example selection, SQL query generation, answer extraction, verification, and iterative refinement. Experiments demonstrate the effectiveness of our approach, achieving 70.5\% accuracy on DataBench QA and 71.6\% on DataBench Lite QA, significantly surpassing baseline scores of 26\% and 27\% respectively. This paper details our methodology, experimental results, and alternative approaches, providing insights into the strengths and limitations of LLM-driven Table QA.
Large language models (LLMs)-empowered autonomous agents are transforming both digital and physical environments by enabling adaptive, multi-agent collaboration. While these agents offer significant opportunities across domains such as finance, healthcare, and smart manufacturing, their unpredictable behaviors and heterogeneous capabilities pose substantial governance and accountability challenges. In this paper, we propose a blockchain-enabled layered architecture for regulatory agent collaboration, comprising an agent layer, a blockchain data layer, and a regulatory application layer. Within this framework, we design three key modules: (i) an agent behavior tracing and arbitration module for automated accountability, (ii) a dynamic reputation evaluation module for trust assessment in collaborative scenarios, and (iii) a malicious behavior forecasting module for early detection of adversarial activities. Our approach establishes a systematic foundation for trustworthy, resilient, and scalable regulatory mechanisms in large-scale agent ecosystems. Finally, we discuss the future research directions for blockchain-enabled regulatory frameworks in multi-agent systems.