On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents

Reinforcement learning (RL) with outcome-based rewards has achieved significant success in training large language model (LLM) agents for complex reasoning tasks. However, in active reasoning where agents need to strategically ask questions to acquire task-relevant information, we find that LLM agents trained with RL often suffer from information self-locking: the agent ceases to ask informative questions and struggles to internalize already-obtained information. To understand the phenomenon, we decompose active reasoning into two core capabilities: Action Selection (AS), which determines the observation stream through queries, and Belief Tracking (BT), which updates the agent's belief based on collected evidence. We show that deficient AS and BT capabilities will limit the information exploration during RL training. Furthermore, insufficient exploration in turn hinders the improvement of AS and BT, creating a feedback loop that locks the agent in a low-information regime. To resolve the issue, we propose a simple yet effective approach that reallocates the learning signal by injecting easy- to-obtain directional critiques to help the agent escape self-locking. Extensive experiments with 7 datasets show that our approach significantly mitigates the information self-locking, bringing up to 60% improvements.

Pairwise Alignment Improves Graph Domain Adaptation

Graph-based methods, pivotal for label inference over interconnected objects in many real-world applications, often encounter generalization challenges, if the graph used for model training differs significantly from the graph used for testing. This work delves into Graph Domain Adaptation (GDA) to address the unique complexities of distribution shifts over graph data, where interconnected data points experience shifts in features, labels, and in particular, connecting patterns. We propose a novel, theoretically principled method, Pairwise Alignment (Pair-Align) to counter graph structure shift by mitigating conditional structure shift (CSS) and label shift (LS). Pair-Align uses edge weights to recalibrate the influence among neighboring nodes to handle CSS and adjusts the classification loss with label weights to handle LS. Our method demonstrates superior performance in real-world applications, including node classification with region shift in social networks, and the pileup mitigation task in particle colliding experiments. For the first application, we also curate the largest dataset by far for GDA studies. Our method shows strong performance in synthetic and other existing benchmark datasets.

GDL-DS: A Benchmark for Geometric Deep Learning under Distribution Shifts

Geometric deep learning (GDL) has gained significant attention in various scientific fields, chiefly for its proficiency in modeling data with intricate geometric structures. Yet, very few works have delved into its capability of tackling the distribution shift problem, a prevalent challenge in many relevant applications. To bridge this gap, we propose GDL-DS, a comprehensive benchmark designed for evaluating the performance of GDL models in scenarios with distribution shifts. Our evaluation datasets cover diverse scientific domains from particle physics and materials science to biochemistry, and encapsulate a broad spectrum of distribution shifts including conditional, covariate, and concept shifts. Furthermore, we study three levels of information access from the out-of-distribution (OOD) testing data, including no OOD information, only OOD features without labels, and OOD features with a few labels. Overall, our benchmark results in 30 different experiment settings, and evaluates 3 GDL backbones and 11 learning algorithms in each setting. A thorough analysis of the evaluation results is provided, poised to illuminate insights for DGL researchers and domain practitioners who are to use DGL in their applications.