Searcharxiv⌕ Search

arXiv subjects

Ronghua Zhang

Publications and source records attributed to Ronghua Zhang.

4 recordsLinked to original sources

Science Prediction Universe

Humanity has long sought to explain natural phenomena. Reliable prediction of experimental outcomes is a central test of our understanding of the processes that produce them. If artificial general intelligence (AGI) is to surpass human scientific capabilities, it must also predict experimental outcomes more reliably than humans. Such capabilities could accelerate scientific discovery across disciplines, help address humanity's most pressing challenges, and improve human well-being. We introduce Science Prediction Universe (SPU), a benchmark of hidden experimental outcomes with 100 public verified tasks from chemistry, materials science, biology and medicine, and 16 private tasks from unpublished wet-lab experiments. Given an experimental setup and candidate conditions, an agent works with any resources it needs to rank the candidates by a measured outcome. We evaluate thirteen agent configurations spanning twelve frontier models across two harnesses (Codex and Claude Code). Current agents remain far from saturating wet-lab outcome prediction, with substantial performance disparities across models: on the public benchmark, configurations separate into two distinct tiers, with task-adjusted Spearman correlations ranging from 0.227 for the lowest-performing configuration to 0.478 for the best. Analysis of 1,155 scored public trajectories (227,103 tool calls) suggests that the bottleneck lies in scientific judgment rather than tool execution: agents rely on shared monotone priors, agreeing far more with one another than with experimental reality (0.52 vs. 0.33), and frequently compute trivial physical or chemical proxies that do not influence the final outcome.

cs.AI↗

Generative discovery of chemical reaction networks

Chemical kinetics determines molecular stability, reaction selectivity and the evolution of reacting mixtures, but discovering the underlying reaction networks remains challenging. Here we introduce ReactNexus, a generative framework for kinetic-guided network exploration starting solely from reactant graphs. Generative models propose transition states and predict the full reaction trajectories connecting reactants and products, while calculations using a machine-learned interatomic potential verify connectivity and evaluate electronic barriers. On an in-distribution benchmark of 10,000 generated candidates, 80.8% connect to the input reactant after density functional theory (DFT) optimization and intrinsic reaction coordinate verification. The resulting networks uncover lower-barrier cooperative pathways and competition between catalyst release and catalyst-bound branches. In the examined carbocation cascades, coverage of known product precursors saturates after limited expansion and distinct entries converge onto shared intermediates, indicating a compact accessible reaction space. Network-derived candidate structures further assist mass-spectral interpretation of a complex nucleophilic aromatic substitution reaction. Together, these results establish a generative approach to reaction-network discovery and mechanistic analysis without predefined products or reaction templates.

q-bio.MN↗

Toward Scalable Multirobot Control: Fast Policy Learning in Distributed MPC

Distributed model predictive control (DMPC) is promising in achieving optimal cooperative control in multirobot systems (MRS). However, real-time DMPC implementation relies on numerical optimization tools to periodically calculate local control sequences online. This process is computationally demanding and lacks scalability for large-scale, nonlinear MRS. This article proposes a novel distributed learning-based predictive control (DLPC) framework for scalable multirobot control. Unlike conventional DMPC methods that calculate open-loop control sequences, our approach centers around a computationally fast and efficient distributed policy learning algorithm that generates explicit closed-loop DMPC policies for MRS without using numerical solvers. The policy learning is executed incrementally and forward in time in each prediction interval through an online distributed actor-critic implementation. The control policies are successively updated in a receding-horizon manner, enabling fast and efficient policy learning with the closed-loop stability guarantee. The learned control policies could be deployed online to MRS with varying robot scales, enhancing scalability and transferability for large-scale MRS. Furthermore, we extend our methodology to address the multirobot safe learning challenge through a force field-inspired policy learning approach. We validate our approach's effectiveness, scalability, and efficiency through extensive experiments on cooperative tasks of large-scale wheeled robots and multirotor drones. Our results demonstrate the rapid learning and deployment of DMPC policies for MRS with scales up to 10,000 units.

cs.RO↗

Differential Type Operators and Gröbner-Shirshov Bases

A long standing problem of Gian-Carlo Rota for associative algebras is the classification of all linear operators that can be defined on them. In the 1970s, there were only a few known operators, for example, the derivative operator, the difference operator, the average operator, and the Rota-Baxter operator. A few more appeared after Rota posed his problem. However, little progress was made to solve this problem in general. In part, this is because the precise meaning of the problem is not so well understood. In this paper, we propose a formulation of the problem using the framework of operated algebras and viewing an associative algebra with a linear operator as one that satisfies a certain operated polynomial identity. This framework also allows us to apply theories of rewriting systems and Gröbner-Shirshov bases. To narrow our focus more on the operators that Rota was interested in, we further consider two particular classes of operators, namely, those that generalize differential or Rota-Baxter operators. As it turns out, these two classes of operators correspond to those that possess Gröbner-Shirshov bases under two different monomial orderings. Working in this framework, and with the aid of computer algebra, we are able to come up with a list of these two classes of operators, and provide some evidence that these lists may be complete. Our search has revealed quite a few new operators of these types whose properties are expected to be similar to the differential operator and Rota-Baxter operator respectively. Recently, a more unified approach has emerged in related areas, such as difference algebra and differential algebra, and Rota-Baxter algebra and Nijenhuis algebra. The similarities in these theories can be more efficiently explored by advances on Rota's problem.

math.RA↗