AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science

Data science plays a critical role in transforming complex data into actionable insights across numerous domains. Recent developments in large language models (LLMs) and artificial intelligence (AI) agents have significantly automated data science workflow. However, it remains unclear to what extent AI agents can match the performance of human experts on domain-specific data science tasks, and in which aspects human expertise continues to provide advantages. We introduce AgentDS, a benchmark and competition designed to evaluate both AI agents and human-AI collaboration performance in domain-specific data science. AgentDS consists of 17 challenges across six industries: commerce, food production, healthcare, insurance, manufacturing, and retail banking. We conducted an open competition involving 29 teams and 80 participants, enabling systematic comparison between human-AI collaborative approaches and AI-only baselines. Our results show that current AI agents struggle with domain-specific reasoning. AI-only baselines perform near or below the median of competition participants, while the strongest solutions arise from human-AI collaboration. These findings challenge the narrative of complete automation by AI and underscore the enduring importance of human expertise in data science, while illuminating directions for the next generation of AI. Visit the AgentDS website here: https://agentds.org/ and open source datasets here: https://huggingface.co/datasets/lainmn/AgentDS .

DA-Mamba: Learning Domain-Aware State Space Model for Global-Local Alignment in Domain Adaptive Object Detection

Domain Adaptive Object Detection (DAOD) aims to transfer detectors from a labeled source domain to an unlabeled target domain. Existing DAOD methods employ multi-granularity feature alignment to learn domain-invariant representations. However, the local connectivity of their CNN-based backbone and detection head restricts alignment to local regions, failing to extract global domain-invariant features. Although transformer-based DAOD methods capture global dependencies via attention mechanisms, their quadratic computational cost hinders practical deployment. To solve this, we propose DA-Mamba, a hybrid CNN-State Space Models (SSMs) architecture that combines the efficiency of CNNs with the linear-time long-range modeling capability of State Space Models (SSMs) to capture both global and local domain-invariant features. Specifically, we introduce two novel modules: Image-Aware SSM (IA-SSM) and Object-Aware SSM (OA-SSM). IA-SSM is integrated into the backbone to enhance global domain awareness, enabling image-level global and local alignment. OA-SSM is inserted into the detection head to model spatial and semantic dependencies among objects, enhancing instance-level alignment. Comprehensive experiments demonstrate that the proposed method can efficiently improve the cross-domain performance of the object detector.

Learning to Jointly Optimize Antenna Positioning and Beamforming for Movable Antenna-Aided Systems

The recently emerged movable antenna (MA) and fluid antenna technologies offer promising solutions to enhance the spatial degrees of freedom in wireless systems by dynamically adjusting the positions of transmit or receive antennas within given regions. In this paper, we aim to address the joint optimization problem of antenna positioning and beamforming in MA-aided multi-user downlink transmission systems. This problem involves mixed discrete antenna position and continuous beamforming weight variables, along with coupled distance constraints on antenna positions, which pose significant challenges for optimization algorithm design. To overcome these challenges, we propose an end-to-end deep learning framework, consisting of a positioning model that handles the discrete variables and the coupled constraints, and a beamforming model that handles the continuous variables. Simulation results demonstrate that the proposed framework achieves superior sum rate performance, yet with much reduced computation time compared to existing methods.

Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interaction

Simulating human conversations using large language models (LLMs) has emerged as a scalable methodology for modeling human social interaction. However, simulating human conversations is challenging because they inherently involve inconsistent and uncollaborative behaviors, such as misunderstandings and interruptions. Analysis comparing inconsistent and uncollaborative behaviors in human- and LLM-generated conversations remains limited, although reproducing these behaviors is integral to simulating human-like and complex social interaction. In this work, we introduce CoCoEval, an evaluation framework that analyzes LLM-simulated conversations by detecting 10 types of inconsistent and uncollaborative behaviors at the turn level using an LLM-as-a-Judge. Using CoCoEval, we evaluate GPT-4.1, GPT-5.1, and Claude Opus 4 by comparing the frequencies of detected behaviors in conversations simulated by each model and in human conversations across academic, business, and governmental meetings, as well as debates. Our analysis shows that (1) under vanilla prompting, LLM-simulated conversations exhibit far fewer inconsistent and uncollaborative behaviors than human conversations; (2) prompt engineering does not provide reliable control over these behaviors, as our results show that different prompts lead to their under- or overproduction; and (3) supervised fine-tuning on human conversations can lead LLMs to overproduce a narrow set of behaviors, such as repetition. Our findings highlight the difficulty of simulating human conversations, raising concerns about the use of LLMs as a proxy for human social interaction.

MedCL-Bench: Benchmarking stability-efficiency trade-offs and scaling in biomedical continual learning

Medical language models must be updated as evidence and terminology evolve, yet sequential updating can trigger catastrophic forgetting. Although biomedical NLP has many static benchmarks, no unified, task-diverse benchmark exists for evaluating continual learning under standardized protocols, robustness to task order and compute-aware reporting. We introduce MedCL-Bench, which streams ten biomedical NLP datasets spanning five task families and evaluates eleven continual learning strategies across eight task orders, reporting retention, transfer, and GPU-hour cost. Across backbones and task orders, direct sequential fine-tuning on incoming tasks induces catastrophic forgetting, causing update-induced performance regressions on prior tasks. Continual learning methods occupy distinct retention-compute frontiers: parameter-isolation provides the best retention per GPU-hour, replay offers strong protection at higher cost, and regularization yields limited benefit. Forgetting is task-dependent, with multi-label topic classification most vulnerable and constrained-output tasks more robust. MedCL-Bench provides a reproducible framework for auditing model updates before deployment.

QiMeng-CodeV-SVA: Training Specialized LLMs for Hardware Assertion Generation via RTL-Grounded Bidirectional Data Synthesis

SystemVerilog Assertions (SVAs) are crucial for hardware verification. Recent studies leverage general-purpose LLMs to translate natural language properties to SVAs (NL2SVA), but they perform poorly due to limited data. We propose a data synthesis framework to tackle two challenges: the scarcity of high-quality real-world SVA corpora and the lack of reliable methods to determine NL-SVA semantic equivalence. For the former, large-scale open-source RTLs are used to guide LLMs to generate real-world SVAs; for the latter, bidirectional translation serves as a data selection method. With the synthesized data, we train CodeV-SVA, a series of SVA generation models. Notably, CodeV-SVA-14B achieves 75.8% on NL2SVA-Human and 84.0% on NL2SVA-Machine in Func.@1, matching or exceeding advanced LLMs like GPT-5 and DeepSeek-R1.

HeartAgent: An Autonomous Agent System for Explainable Differential Diagnosis in Cardiology

Heart diseases remain a leading cause of morbidity and mortality worldwide, necessitating accurate and trustworthy differential diagnosis. However, existing artificial intelligence-based diagnostic methods are often limited by insufficient cardiology knowledge, inadequate support for complex reasoning, and poor interpretability. Here we present HeartAgent, a cardiology-specific agent system designed to support a reliable and explainable differential diagnosis. HeartAgent integrates customized tools and curated data resources and orchestrates multiple specialized sub-agents to perform complex reasoning while generating transparent reasoning trajectories and verifiable supporting references. Evaluated on the MIMIC dataset and a private electronic health records cohort, HeartAgent achieved over 36% and 20% improvements over established comparative methods, in top-3 diagnostic accuracy, respectively. Additionally, clinicians assisted by HeartAgent demonstrated gains of 26.9% in diagnostic accuracy and 22.7% in explanatory quality compared with unaided experts. These results demonstrate that HeartAgent provides reliable, explainable, and clinically actionable decision support for cardiovascular care.

3-D Trajectory Optimization for Robust Direction Sensing in Movable Antenna Systems

This paper presents a novel wireless sensing system where a movable antenna (MA) continuously moves and receives sensing signals within a three-dimensional (3-D) region to enhance sensing performance compared with conventional fixed-position antenna (FPA)-based sensing. We show that the performance of direction vector estimation for a target is fundamentally related to the 3-D MA trajectory in terms of the mean square angular error lower-bound (MSAEB), which is adopted as a coordinate-invariant performance metric. In particular, the closed-form expression of the MSAEB is derived as a function of the trajectory covariance matrix. Theoretical analysis shows that two-dimensional (2-D) antenna movement suffers from performance divergence for target direction close to the endfire direction of the 2-D MA plane, whereas 3-D movement can achieve isotropic sensing performance over the entire angular region. To achieve robust sensing performance, we formulate a min-max optimization problem to minimize the maximum (worst-case) MSAEB over a given continuous angular region wherein the target is located. An efficient successive convex approximation (SCA) algorithm is developed to optimize the 3-D MA trajectory and obtain a locally optimal solution. Numerical results demonstrate that the proposed 3-D MA sensing scheme is able to significantly reduce the worst-case mean square angular error (MSAE) compared with conventional arrays with FPAs and MA systems with 2-D movement only, thus achieving more accurate and robust direction estimation over the entire angular region.

Efficient, Adaptive Near-Field Beam Training based on Linear Bandit

This letter proposes a linear bandit-based beam training framework for near-field communication under multi-path channels. By leveraging Thompson Sampling (TS), the framework adaptively balances exploration and exploitation to maximize cumulative beamforming gain under limited pilot overhead. To ensure data-efficient learning, we incorporate a correlated Gaussian prior in the DFT domain, using a Gaussian kernel to capture spatial correlations and near-field energy leakage. We develop three TS strategies: codebook-constrained search for rapid convergence via structural regularization, continuous-space search to achieve near-optimal performance, and a two-stage hybrid refinement scheme that balances convergence speed and estimation accuracy. Simulation results show that the proposed framework reduces pilot overhead by up to 90\% while achieving more than a 2dB SNR gain over baselines in multipath environments. Furthermore, the continuous-space search is shown to be asymptotically optimal, approaching the full-CSI bound when the pilot overhead is unconstrained.

Estimation of heterogeneous principal effects under principal ignorability

We study estimation and inference for heterogeneous principal causal effects with binary treatments and binary intermediate variables. Principal causal effects are subgroup effects within strata defined by potential values of an intermediate variable, including effects among compliers. We propose a framework for estimating and forming pointwise confidence intervals for heterogeneous principal causal effects under the principal ignorability assumption. Several estimators are developed, and their robustness properties are characterized: one estimator is doubly robust, whereas the other two attain intermediate robustness between double and triple robustness; in contrast, principal causal effects can be estimated in a triply robust manner only. We establish large-sample theory under nonparametric smoothness conditions and analyze the bias contributions of each approach, providing insight into performance beyond the smooth setting, including in high-dimensional regimes. Camden Coalition hotspotting randomized trial are used to illustrate the methods by estimating heterogeneous complier effects.