Deyu Zou

Newman Cheng, Gordon Broadbent, Jason Dong et al.

We present Cognitive Loop via In-Situ Optimization (CLIO), an agent that couples a continuously-updated belief-state graph with a recursive plan-then-act loop. The result is a reasoning agent that can contribute something qualitatively different, which we term \emph{calibrated deference}: the capacity to recognize when its own tools or assumptions are failing, to adapt its strategy in response, and to generate mechanistic hypotheses that guide experimental revision. We tested CLIO in a closed-loop human-AI campaign to design an aqueous organic redox flow battery (AORFB) negolyte, with CLIO leading proposal and interpretation in close partnership with chemists who synthesized, characterized, and weighed in on design choices. Across 17 candidates over three rounds, CLIO converged on a top phosphonate candidate; characterization confirmed a 130~mV improvement in redox potential over the literature baseline. Characterization then revealed unexpectedly poor electrochemical reversibility -- a regression no property predictor had flagged. CLIO generated competing mechanistic hypotheses, prioritized discriminating diagnostics, traced the failure to phosphonate-potassium ion pairing, and prescribed a sulfonate replacement. The resulting compound showed substantially improved electrochemical reversibility and maintained a 90~mV improvement in redox potential, closing the design-make-test-redesign loop.

Deyu Zou, Yongqiang Chen, Fan Feng et al. · gatech

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.

Deyu Zou, Shikun Liu, Siqi Miao et al.

Geometric deep learning (GDL) has gained significant attention in scientific fields, for its proficiency in modeling data with intricate geometric structures. However, very few works have delved into its capability of tackling the distribution shift problem, a prevalent challenge in many applications. To bridge this gap, we propose GeSS, a comprehensive benchmark designed for evaluating the performance of GDL models in scientific scenarios with distribution shifts. Our evaluation datasets cover diverse scientific domains from particle physics, 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) test data, including no OOD information, only unlabeled OOD data, and OOD data 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 GDL researchers and domain practitioners who are to use GDL in their applications.

Shikun Liu, Deyu Zou, Han Zhao et al.

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.

Deyu Zou, Yongqiang Chen, Mufei Li et al. · gatech

Graph-based retrieval-augmented generation (RAG) enables large language models (LLMs) to ground responses with structured external knowledge from up-to-date knowledge graphs (KGs) and reduce hallucinations. However, LLMs often rely on a weak retriever in graph-based RAG: I) Due to the lack of ground truth, the retriever is often trained on weak supervision, which often introduces spurious signals to the LLMs. II) Due to the abstraction of graph data, the retrieved knowledge is often presented in unorganized forms. To mitigate the issue, we present Refined Graph-based RAG (ReG) to align weak retrievers to LLMs for graph-based RAG. Specifically, ReG incorporates LLM feedback to get rid of spurious signals and improve the quality of the supervision. Meanwhile, ReG introduces a structure-aware reorganization module to refactor the retrieval results into logically coherent evidence chains. Experiments on prominent benchmarks demonstrate that ReG significantly and consistently brings improvements across different LLM backbones by up to 10%. The improved supervision quality enables ReG to match the state-of-the-art performance with 5% training data and to transfer to out-of-distribution KGs. Notably, when adopted to reasoning-based LLMs, ReG reduces the reasoning token cost by up to 30% and improves the performance by up to 4%.

Deyu Zou, Yongqiang Chen, Jianxiang Wang et al. · gatech

Active reasoning requires large language models (LLMs) to interact with external sources and strategically gather information to solve problems. Central to this process is belief tracking: maintaining a coherent understanding of the problem state and the missing information toward the solution. However, due to limited reasoning capabilities, LLM-based agents often suffer from belief deviation: they struggle to correctly model beliefs, lose track of problem states, and fall into uninformative or repetitive actions. Once this happens, errors compound and reinforcement learning (RL) training fails to properly credit the crucial exploratory steps. To address this issue, we propose to track the deviation of model beliefs and develop $\mathbf{T^3}$, a simple yet effective method that detects excessive belief deviation and truncates trajectories during training to remove uninformative tails. By preserving credit for informative prefixes, $\mathbf{T^3}$ systematically improves policy optimization. Across 5 challenging tasks, $\mathbf{T^3}$ consistently enhances training stability, token efficiency, and final performance, achieving up to 30% gains while cutting rollout tokens by roughly 25%. These results highlight belief control as a key principle for developing robust and generalizable LLM-based active reasoners.

Shikun Liu, Deyu Zou, Nima Shoghi et al.

In the era of foundation models, fine-tuning pre-trained models for specific downstream tasks has become crucial. This drives the need for robust fine-tuning methods to address challenges such as model overfitting and sparse labeling. Molecular graph foundation models (MGFMs) face unique difficulties that complicate fine-tuning. These models are limited by smaller pre-training datasets and more severe data scarcity for downstream tasks, both of which require enhanced model generalization. Moreover, MGFMs must accommodate diverse objectives, including both regression and classification tasks. To better understand and improve fine-tuning techniques under these conditions, we classify eight fine-tuning methods into three mechanisms: weight-based, representation-based, and partial fine-tuning. We benchmark these methods on downstream regression and classification tasks across supervised and self-supervised pre-trained models in diverse labeling settings. This extensive evaluation provides valuable insights and informs the design of a refined robust fine-tuning method, ROFT-MOL. This approach combines the strengths of simple post-hoc weight interpolation with more complex weight ensemble fine-tuning methods, delivering improved performance across both task types while maintaining the ease of use inherent in post-hoc weight interpolation.