A natural way to unlock particular capabilities is to improve this training data.

We introduce a comprehensive continual learning dataset and benchmark (CurlL) grounded in human developmental trajectories from ages 5-10, enabling systematic and fine-grained assessment of models' ability to progressively acquire new skills. CurlL spans five developmental stages (0-4) covering ages 5-10, supported by a skill graph that breaks down broad skills into smaller abilities, concrete goals, and measurable indicators, while also capturing which abilities build on others. We generate a 23.4B-token synthetic dataset with controlled skill progression, vocabulary complexity, and format diversity, comprising paragraphs, comprehension-based QA (CQA), skill-testing QA (CSQA), and instruction-response (IR) pairs. Stage-wise token counts range from 2.12B to 6.78B tokens, supporting precise analysis of forgetting, forward transfer, and backward transfer. Using a 135M-parameter transformer trained under independent, joint, and sequential (continual) setups, we show trade-offs in skill retention and transfer efficiency. By mirroring human learning patterns and providing fine-grained control over skill dependencies, this work advances continual learning evaluations for language models.

A natural way to unlock particular capabilities is to improve this training data.

Multi-task multi-agent reinforcement learning (MT-MARL) has recently gained attention for its potential to enhance MARL's adaptability across multiple tasks. However, it is challenging for existing multi-task learning methods to handle complex problems, as they are unable to handle unrelated tasks and possess limited knowledge transfer capabilities. In this paper, we propose a hierarchical approach that efficiently addresses these challenges. The high-level module utilizes a skill graph, while the low-level module employs a standard MARL algorithm. Our approach offers two contributions. First, we consider the MT-MARL problem in the context of unrelated tasks, expanding the scope of MTRL. Second, the skill graph is used as the upper layer of the standard hierarchical approach, with training independent of the lower layer, effectively handling unrelated tasks and enhancing knowledge transfer capabilities. Extensive experiments are conducted to validate these advantages and demonstrate that the proposed method outperforms the latest hierarchical MAPPO algorithms. Videos and code are available at https://github.com/WindyLab/MT-MARL-SG

--This paper presents NeSyPack, a neuro-symbolic framework for bimanual logistics packing. Our NeSyPack combines data-driven models and symbolic reasoning to build an explainable hierarchical framework that is generalizable, data-efficient, and reliable. It decomposes a task into subtasks via hierarchical reasoning, and further into atomic skills managed by a symbolic skill graph. The graph selects skill parameters, robot configurations, and task-specific control strategies for execution. This modular design enables robustness, adaptability, and efficient reuse--outperforming end-to-end models that require large-scale retraining. Using NeSyPack, our team won the First Prize in the What Bimanuals Can Do (WBCD) competition at the 2025 IEEE International Conference on Robotics & Automation (ICRA). Logistics packing is a crucial task in the warehouse industry, which requires personnel to select the appropriate items and pack them into a shipping box.

High-quality data plays a critical role in the pretraining and fine-tuning of large language models (LLMs), even determining their performance ceiling to some degree. Consequently, numerous data selection methods have been proposed to identify subsets of data that can effectively and efficiently enhance model performance. However, most of these methods focus on general data selection and tend to overlook the specific nuances of domain-related data. In this paper, we introduce MASS, a \textbf{MA}thematical data \textbf{S}election framework using the \textbf{S}kill graph for pretraining LLMs in the mathematical reasoning domain. By taking into account the unique characteristics of mathematics and reasoning, we construct a skill graph that captures the mathematical skills and their interrelations from a reference dataset. This skill graph guides us in assigning quality scores to the target dataset, enabling us to select the top-ranked subset which is further used to pretrain LLMs. Experimental results demonstrate the efficiency and effectiveness of MASS across different model sizes (1B and 7B) and pretraining datasets (web data and synthetic data). Specifically, in terms of efficiency, models trained on subsets selected by MASS can achieve similar performance to models trained on the original datasets, with a significant reduction in the number of trained tokens - ranging from 50\% to 70\% fewer tokens. In terms of effectiveness, when trained on the same amount of tokens, models trained on the data selected by MASS outperform those trained on the original datasets by 3.3\% to 5.9\%. These results underscore the potential of MASS to improve both the efficiency and effectiveness of pretraining LLMs.

We present Dynamic Skill Adaptation (DSA), an adaptive and dynamic framework to adapt novel and complex skills to Large Language Models (LLMs). Compared with previous work which learns from human-curated and static data in random orders, we propose to first automatically generate and organize the training data by mimicking the learning pathways of human and then dynamically tailor the training data based on the training dynamics. Specifically, inspired by the learning structures and teaching strategies in the human education system, we first construct a skill graph by decomposing complex skills into sub-skills and arranging them based on their dependencies in human syllables. For every skill, we utilize LLMs to generate both textbook-like data which contains detailed descriptions of skills for pre-training and exercise-like data which targets at explicitly utilizing the skills to solve problems for instruction-tuning. Furthermore, during the instruction-tuning, we dynamically update the training data which down-weight easy-to-learn examples, generate more complex examples, and filter out data with errors. Experiments on large language models such as LLAMA and Mistral demonstrate the effectiveness of our proposed methods in adapting math reasoning skills and social study skills.

The development of autonomous and remote-operated driving systems requires extensive stakeholder analyses, requirement engineering, and formalized system descriptions. This is necessary to guarantee the success of the final product after the expensive and time-consuming development phase. To integrate a formalized description of the required abilites of the system, ability graphs have been proposed in the literature. Up to this date, however, this ability graph has only been used to model less complicated driver assistance systems in the literature. This work aims to introduce the value of an ability graph-based description of complex driving systems. This is achieved by successfully demonstrating and discussing a method for constructing a holistic ability graph capable of describing the entirety of abilities required for any driving system.

Assembling a slave object into a fixture-free master object represents a critical challenge in flexible manufacturing. Existing deep reinforcement learning-based methods, while benefiting from visual or operational priors, often struggle with small-batch precise assembly tasks due to their reliance on insufficient priors and high-costed model development. To address these limitations, this paper introduces a cognitive manipulation and learning approach that utilizes skill graphs to integrate learning-based object detection with fine manipulation models into a cohesive modular policy. This approach enables the detection of the master object from both global and local perspectives to accommodate positional uncertainties and variable backgrounds, and parametric residual policy to handle pose error and intricate contact dynamics effectively. Leveraging the skill graph, our method supports knowledge-informed learning of semi-supervised learning for object detection and classroom-to-real reinforcement learning for fine manipulation. Simulation experiments on a gear-assembly task have demonstrated that the skill-graph-enabled coarse-operation planning and visual attention are essential for efficient learning and robust manipulation, showing substantial improvements of 13$\%$ in success rate and 15.4$\%$ in number of completion steps over competing methods. Real-world experiments further validate that our system is highly effective for robotic assembly in semi-structured environments.

We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inefficient. To tackle this challenge, we convert the multi-task learning problem into learning basic skills and planning over the skills. Using the popular open-world game Minecraft as the testbed, we propose three types of fine-grained basic skills, and use RL with intrinsic rewards to acquire skills. A novel Finding-skill that performs exploration to find diverse items provides better initialization for other skills, improving the sample efficiency for skill learning. In skill planning, we leverage the prior knowledge in Large Language Models to find the relationships between skills and build a skill graph. When the agent is solving a task, our skill search algorithm walks on the skill graph and generates the proper skill plans for the agent. In experiments, our method accomplishes 40 diverse Minecraft tasks, where many tasks require sequentially executing for more than 10 skills. Our method outperforms baselines by a large margin and is the most sample-efficient demonstration-free RL method to solve Minecraft Tech Tree tasks. The project's website and code can be found at https://sites.google.com/view/plan4mc.