11 papers
Same Winners, Different Success Rates: Evaluating How LLM Agents Recover from Failures
Dong Xu, Zhangfan Yang, Jiantao Wu +5
Evaluating how LLM agents recover from mid-task failures is central to deploying reliable agentic systems. Existing checkpoint-based benchmarks measure recovery by comparing which…
ReplayLens: Auditing Agents' Use of Outcomes
Dong Xu, Zhangfan Yang, Jiantao Wu +5
When an agent reuses logged experience, a changed decision may reflect the recorded score, the action's name, or the record's position in storage. Standard memory evaluations do no…
RoutePrism: Tracing Construction Order Effects in Agent Memory
Dong Xu, Zhangfan Yang, Jiantao Wu +5
Processing the same records in a different order can discard different evidence, yet endpoint accuracy alone cannot reveal what changed or whether it mattered. We introduce RoutePr…
DegradeQuery: Counterfactual Tuple Pretraining for Context-Aware PROTAC Degradation Prediction
Dong Xu, Zhangfan Yang, Jiantao Wu +3
Proteolysis-targeting chimeras (PROTACs) induce protein degradation by recruiting a target protein to an E3 ubiquitin ligase, making degradation a joint outcome of the degrader mol…
BioLM-Score: Language-Prior Conditioned Probabilistic Geometric Potentials for Protein-Ligand Scoring
Zhangfan Yang, Baoyun Chen, Dong Xu +4
Protein-ligand scoring is a central component of structure-based drug design, underpinning molecular docking, virtual screening, and pose optimization. Conventional physics-based e…
From Tokens to Blocks: A Block-Diffusion Perspective on Molecular Generation
Qianwei Yang, Dong Xu, Zhangfan Yang +4
Drug discovery can be viewed as a combinatorial search over an immense chemical space, motivating the development of deep generative models for de novo molecular design. Among thes…
Toward Closed-loop Molecular Discovery via Language Model, Property Alignment and Strategic Search
Junkai Ji, Zhangfan Yang, Dong Xu +4
Drug discovery is a time-consuming and expensive process, with traditional high-throughput and docking-based virtual screening hampered by low success rates and limited scalability…
IBEX: Information-Bottleneck-EXplored Coarse-to-Fine Molecular Generation under Limited Data
Dong Xu, Zhangfan Yang, Jenna Xinyi Yao +3
Three-dimensional generative models increasingly drive structure-based drug discovery, yet it remains constrained by the scarce publicly available protein-ligand complexes. Under s…
MODA: A Unified 3D Diffusion Framework for Multi-Task Target-Aware Molecular Generation
Dong Xu, Zhangfan Yang, Sisi Yuan +3
Three-dimensional molecular generators based on diffusion models can now reach near-crystallographic accuracy, yet they remain fragmented across tasks. SMILES-only inputs, two-stag…
READ: A Retrieval-Alignment Diffusion Framework for Structure-based Drug Design
Dong Xu, Zhangfan Yang, Junchuang Cai +4
Structure-based drug design (SBDD) models are central to modern pharmaceutical research, enabling the rational exploration of protein-ligand interactions at atomic resolution. Howe…
Dockformer: A transformer-based molecular docking paradigm for large-scale virtual screening
Zhangfan Yang, Junkai Ji, Shan He +5
Molecular docking is a crucial step in drug development, which enables the virtual screening of compound libraries to identify potential ligands that target proteins of interest. H…