12 papers · ranked by Valyu relevance
Jiayu Wang, Yifei Ming, Riya Dulepet, Qinglin Chen + 6 more
Deep research—producing comprehensive, citation-grounded reports by searching and synthesizing information from hundreds of live web sources—marks an important frontier for agentic systems. To rigorously evaluate this ability, four principles are essential: tasks should be (1) user-centric, reflecting realistic…
Sergio Gómez González, Miguel Domingo, Francisco Casacuberta
Comparative evaluation of several systems is a recurrent task in researching. It is a key step before deciding which system to use for our work, or, once our research has been conducted, to demonstrate the potential of the resulting model. Furthermore, it is the main task of competitive, public challenges evaluation.…
Zhizheng Wang, Chih-Hsuan Wei, Joey Chan, Robert Leaman + 18 more
Trustworthiness and transparency are essential for the clinical adoption of artificial intelligence (AI) in healthcare and biomedical research. Recent deep research systems aim to accelerate evidence-grounded scientific discovery by integrating AI agents with multi-hop information retrieval, reasoning, and synthesis.…
Zaw Myo Hein, Dhanyashri Guruparan, Blaire Okunsai, Che Mohd Nasril Che Mohd Nassir + 4 more
Simple Summary Artificial intelligence (AI) and machine learning (ML), particularly deep learning methods like neural networks and transformers, are revolutionizing biology by analyzing massive amounts genetic and protein data. These technologies enhance the prediction of gene functions, the identification of…
Saimun Habib, Vaishak Belle, Fengxiang He
Neurosymbolic systems such as DeepProbLog combine neural perception with probabilistic logic, but standard inference is associational. Counterfactual reasoning additionally requires a causal semantics for interventions and evidence. We introduce DeepSWIP, a single-world counterfactual semantics for DeepProbLog…
Dipayan Sarkar, Koushik Bardhan, Chiranjib Sarkar
Deep learning has rapidly become essential for predicting biomolecular interactions; however, most web-tools expose only a single, pre-built model with a fixed, non-configurable architecture that users cannot redesign, retrain on their own data, or compare; they are typically dedicated to one interaction type and often…
Yigeng Jiang, Tengchao Yang, Taoyong Cui, Jiaxing Wan + 24 more
Deep research agents are Large Language Model (LLM)-based systems designed for autonomous, multi-step scientific reasoning, and they hold immense potential for accelerating research in the physical sciences. However, comprehensive and in-depth evaluations of their capabilities within this domain remain lacking. To…
Xiaopeng Xu, Chenjie Feng, Chao Zha, Wenjia He + 3 more
Computational protein design is often constrained by slow, complex, inaccessible, and highly sophiscated and expert-dependent workflows that hinder its transferrability and generalization power for broader applications. We present ProteinMCP, an agentic AI framework designed to accelerate and democratize protein…
Zhichao Lin, Zhichao Liang, Gaoqiang Liu, Meng Xu + 3 more
As agentic foundation models continue to evolve, how to further improve their performance in vertical domains has become an important challenge. To this end, building upon Tongyi DeepResearch, a powerful agentic foundation model, we focus on the Chinese medical deep search scenario and propose QuarkMedSearch…
Jeonghyeon Kim, Philip Romero
Large language models (LLMs) are increasingly deployed as agents for scientific discovery, but standardized frameworks for evaluating their performance and behavior in scientific workflows are lacking. Protein design provides a demanding test case because modern workflows combine stochastic generative models, structure…
Shi, Jinxin, Zongsheng Cao, Runsheng Ma + 7 more
The deep-research framework orchestrates external tools to perform complex, multi-step scientific reasoning that exceeds the native limits of a single large language model. However, it still suffers from context pollution, weak evidentiary support, and brittle execution paths. To address these issues, we propose…
Ruijie Cao, Tong Jin, Fengyuan Xin, Yiwei Hou + 16 more
Three-dimensional (3D) imaging represents the development of next generation of fluorescence microscopy. However, routine axial down-sampling makes isotropic resolution unrealistic. Here, we propose DeepUI, a physical zero-shot framework designed to achieve isotropic 3D fluorescence images from a low axial sampling…