M3-BENCH: Process-Aware Evaluation of LLM Agents Social Behaviors in Mixed-Motive Games

As the capabilities of large language model (LLM) agents continue to advance, their advanced social behaviors, such as cooperation, deception, and collusion, call for systematic evaluation. However, existing benchmarks often emphasize a single capability dimension or rely solely on behavioral outcomes, overlooking rich process information from agents' decision reasoning and communicative interactions. To address this gap, we propose M3-Bench, a multi-stage benchmark for mixed-motive games, together with a process-aware evaluation framework that conducts synergistic analysis across three modules: BTA (Behavioral Trajectory Analysis), RPA (Reasoning Process Analysis), and CCA (Communication Content Analysis). Furthermore, we integrate the Big Five personality model and Social Exchange Theory to aggregate multi-dimensional evidence into interpretable social behavior portraits, thereby characterizing agents' personality traits and capability profiles beyond simple task scores or outcome-based metrics. Experimental results show that M3-Bench can reliably distinguish diverse social behavior competencies across models, and it reveals that some models achieve seemingly reasonable behavioral outcomes while exhibiting pronounced inconsistencies in their reasoning and communication.

BabyVision: Visual Reasoning Beyond Language

While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses across four key categories. Empirical results and human evaluation reveal that leading MLLMs perform significantly below human baselines. Gemini3-Pro-Preview scores 49.7, lagging behind 6-year-old humans and falling well behind the average adult score of 94.1. These results show despite excelling in knowledge-heavy evaluations, current MLLMs still lack fundamental visual primitives. Progress in BabyVision represents a step toward human-level visual perception and reasoning capabilities. We also explore solving visual reasoning with generation models by proposing BabyVision-Gen and automatic evaluation toolkit. Our code and benchmark data are released at https://github.com/UniPat-AI/BabyVision for reproduction.

MDAgent2: Large Language Model for Code Generation and Knowledge Q&A in Molecular Dynamics

Molecular dynamics (MD) simulations are essential for understanding atomic-scale behaviors in materials science, yet writing LAMMPS scripts remains highly specialized and time-consuming tasks. Although LLMs show promise in code generation and domain-specific question answering, their performance in MD scenarios is limited by scarce domain data, the high deployment cost of state-of-the-art LLMs, and low code executability. Building upon our prior MDAgent, we present MDAgent2, the first end-to-end framework capable of performing both knowledge Q&A and code generation within the MD domain. We construct a domain-specific data-construction pipeline that yields three high-quality datasets spanning MD knowledge, question answering, and code generation. Based on these datasets, we adopt a three stage post-training strategy--continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL)--to train two domain-adapted models, MD-Instruct and MD-Code. Furthermore, we introduce MD-GRPO, a closed-loop RL method that leverages simulation outcomes as reward signals and recycles low-reward trajectories for continual refinement. We further build MDAgent2-RUNTIME, a deployable multi-agent system that integrates code generation, execution, evaluation, and self-correction. Together with MD-EvalBench proposed in this work, the first benchmark for LAMMPS code generation and question answering, our models and system achieve performance surpassing several strong baselines.This work systematically demonstrates the adaptability and generalization capability of large language models in industrial simulation tasks, laying a methodological foundation for automatic code generation in AI for Science and industrial-scale simulations. URL: https://github.com/FredericVAN/PKU_MDAgent2

RAGSynth: Synthetic Data for Robust and Faithful RAG Component Optimization

RAG can enhance the performance of LLMs on knowledge-intensive tasks. Various RAG paradigms, including vanilla, planning-based, and iterative RAG, are built upon 2 cores: the retriever, which should robustly select relevant documents across complex queries, and the generator, which should faithfully synthesize responses. However, existing retrievers rely heavily on public knowledge and struggle with queries of varying logical complexity and clue completeness, while generators frequently face fidelity problems. In this work, we introduce RAGSynth, a framework that includes a data construction modeling and a corresponding synthetic data generation implementation, designed to optimize retriever robustness and generator fidelity. Additionally, we present SynthBench, a benchmark encompassing 8 domain-specific documents across 4 domains, featuring diverse query complexities, clue completeness, and fine-grained citation granularity. Leveraging RAGSynth, we generate a large-scale synthetic dataset, including single and multi-hop. Extensive experiments demonstrate that the synthetic data significantly improves the robustness of the retrievers and the fidelity of the generators. Additional evaluations confirm that RAGSynth can also generalize well across different domains. By integrating the optimized retrievers into various RAG paradigms, we consistently observe enhanced RAG system performance. We have open-sourced the implementation on https://github.com/EachSheep/RAGSynth.

MASS: Multi-Agent Simulation Scaling for Portfolio Construction

LLM-based multi-agent has gained significant attention for their potential in simulation and enhancing performance. However, existing works are limited to pure simulations or are constrained by predefined workflows, restricting their applicability and effectiveness. In this paper, we introduce the Multi-Agent Scaling Simulation (MASS) for portfolio construction. MASS achieves stable and continuous excess returns by progressively increasing the number of agents for large-scale simulations to gain a superior understanding of the market and optimizing agent distribution end-to-end through a reverse optimization process, rather than relying on a fixed workflow. We demonstrate its superiority through performance experiments, ablation studies, backtesting experiments, experiments on updated data and stock pools, scaling experiments, parameter sensitivity experiments, and visualization experiments, conducted in comparison with 6 state-of-the-art baselines on 3 challenging A-share stock pools. We expect the paradigm established by MASS to expand to other tasks with similar characteristics. The implementation of MASS has been open-sourced at https://github.com/gta0804/MASS.

PixelWeb: The First Web GUI Dataset with Pixel-Wise Labels

Graphical User Interface (GUI) datasets are crucial for various downstream tasks. However, GUI datasets often generate annotation information through automatic labeling, which commonly results in inaccurate GUI element BBox annotations, including missing, duplicate, or meaningless BBoxes. These issues can degrade the performance of models trained on these datasets, limiting their effectiveness in real-world applications. Additionally, existing GUI datasets only provide BBox annotations visually, which restricts the development of visually related GUI downstream tasks. To address these issues, we introduce PixelWeb, a large-scale GUI dataset containing over 100,000 annotated web pages. PixelWeb is constructed using a novel automatic annotation approach that integrates visual feature extraction and Document Object Model (DOM) structure analysis through two core modules: channel derivation and layer analysis. Channel derivation ensures accurate localization of GUI elements in cases of occlusion and overlapping elements by extracting BGRA four-channel bitmap annotations. Layer analysis uses the DOM to determine the visibility and stacking order of elements, providing precise BBox annotations. Additionally, PixelWeb includes comprehensive metadata such as element images, contours, and mask annotations. Manual verification by three independent annotators confirms the high quality and accuracy of PixelWeb annotations. Experimental results on GUI element detection tasks show that PixelWeb achieves performance on the mAP95 metric that is 3-7 times better than existing datasets. We believe that PixelWeb has great potential for performance improvement in downstream tasks such as GUI generation and automated user interaction.

ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents

Recent advancements in integrating large language models (LLMs) with application programming interfaces (APIs) have gained significant interest in both academia and industry. These API-based agents, leveraging the strong autonomy and planning capabilities of LLMs, can efficiently solve problems requiring multi-step actions. However, their ability to handle multi-dimensional difficulty levels, diverse task types, and real-world demands through APIs remains unknown. In this paper, we introduce \textsc{ShortcutsBench}, a large-scale benchmark for the comprehensive evaluation of API-based agents in solving tasks with varying levels of difficulty, diverse task types, and real-world demands. \textsc{ShortcutsBench} includes a wealth of real APIs from Apple Inc.'s operating systems, refined user queries from shortcuts, human-annotated high-quality action sequences from shortcut developers, and accurate parameter filling values about primitive parameter types, enum parameter types, outputs from previous actions, and parameters that need to request necessary information from the system or user. Our extensive evaluation of agents built with $5$ leading open-source (size >= 57B) and $4$ closed-source LLMs (e.g. Gemini-1.5-Pro and GPT-3.5) reveals significant limitations in handling complex queries related to API selection, parameter filling, and requesting necessary information from systems and users. These findings highlight the challenges that API-based agents face in effectively fulfilling real and complex user queries. All datasets, code, and experimental results will be available at \url{https://github.com/eachsheep/shortcutsbench}.