Vision-language models have demonstrated impressive capabilities as computer-use agents (CUAs) capable of automating diverse computer tasks. As their commercial potential grows, critical details of the most capable CUA systems remain closed. As these agents will increasingly mediate digital interactions and execute consequential decisions on our behalf, the research community needs access to open CUA frameworks to study their capabilities, limitations, and risks. To bridge this gap, we propose OpenCUA, a comprehensive open-source framework for scaling CUA data and foundation models. Our framework consists of: (1) an annotation infrastructure that seamlessly captures human computer-use demonstrations; (2) AgentNet, the first large-scale computer-use task dataset spanning 3 operating systems and 200+ applications and websites; (3) a scalable pipeline that transforms demonstrations into state–action pairs with reflective long Chain-of-Thought reasoning that sustain robust performance gains as data scales. Our end-to-end agent models demonstrate strong performance across CUA benchmarks. In particular, OpenCUA-72B achieves an average success rate of 45.0% on OSWorld‑Verified, establishing a new state-of-the-art (SOTA) among open-source models. Further analysis confirms that our approach generalizes well across domains and benefits significantly from increased test-time computation. We release our annotation tool, datasets, code, and models to build open foundations for further CUA research.

Finding the maximum cut of a graph (MAXCUT) is a classic optimization problem that has motivated parallel algorithm development. While approximate algorithms to MAXCUT offer attractive theoretical guarantees and demonstrate compelling empirical performance, such approximation approaches can shift the dominant computational cost to the stochastic sampling operations. Neuromorphic computing, which uses the organizing principles of the nervous system to inspire new parallel computing architectures, offers a possible solution. One ubiquitous feature of natural brains is stochasticity: the individual elements of biological neural networks possess an intrinsic randomness that serves as a resource enabling their unique computational capacities. By designing circuits and algorithms that make use of randomness similarly to natural brains, we hypothesize that the intrinsic randomness in microelectronics devices could be turned into a valuable component of a neuromorphic architecture enabling more efficient computations. Here, we present neuromorphic circuits that transform the stochastic behavior of a pool of random devices into useful correlations that drive stochastic solutions to MAXCUT. We show that these circuits perform favorably in comparison to software solvers and argue that this neuromorphic hardware implementation provides a path for scaling advantages. This work demonstrates the utility of combining neuromorphic principles with intrinsic randomness as a computational resource for new computational architectures.

We consider the maximum flow problem in directed planar graphs with capacities on both vertices and arcs and with multiple sources and sinks. We present three algorithms when the capacities are integers. The first algorithm runs in O ( min { k 2 n , n log 3 n + kn }) time when all capacities are bounded by a constant, where n is the number of vertices in the graph, and k is the number of terminals. This algorithm is the first to solve the vertex-disjoint paths problem in linear time when k is fixed but larger than 2. The second algorithm runs in O ( k 5 Δ n polylog ( nU )) time, where each arc capacity and finite vertex capacity is bounded by U , and Δ is the maximum degree of the graph. Finally, when k = 3, we present an algorithm that runs in O ( n log n ) time; this algorithm works even when the capacities are arbitrary reals. Our algorithms improve on the fastest previously known algorithms when k and Δ are fixed and U is bounded by a polynomial in n . Prior to this result, the fastest algorithms ran in O ( n 4/3+ o (1) ) time for unit capacities; in the smallest of O ( n 3/2 log n log U ), Õ( n 10/7 U 1/7 ), O ( n 11/8+o(1) U 1/4 ), and O ( n 4/3 + o(1) U 1/3 ) time for integer capacities; and in O ( n 2 /log n ) time for real capacities, even when k = 3.

We present a theoretical framework for designing and assessing the performance of algorithms executing in networks consisting of spiking artificial neurons. Although spiking neural networks (SNNs) are capable of general-purpose computation, few algorithmic results with rigorous asymptotic performance analysis are known. SNNs are exceptionally well-motivated practically, as neuromorphic computing systems with 100 million spiking neurons are available, and systems with a billion neurons are anticipated in the next few years. Beyond massive parallelism and scalability, neuromorphic computing systems offer energy consumption orders of magnitude lower than conventional high-performance computing systems. We employ our framework to design and analyze neuromorphic graph algorithms, focusing on shortest path problems. Our neuromorphic algorithms are message-passing algorithms relying critically on data movement for computation, and we develop data-movement lower bounds for conventional algorithms. A fair and rigorous comparison with conventional algorithms and architectures is challenging but paramount. We prove a polynomial-factor advantage even when we assume an SNN consisting of a simple grid-like network of neurons. To the best of our knowledge, this is one of the first examples of a provable asymptotic computational advantage for neuromorphic computing.

Neuromorphic computing offers the potential of an unprecedented level of parallelism at a local scale. Although in their infancy, current first-generation neuromorphic processing units (NPUs) deliver as many as 128K artificial neurons in a package smaller than current laptop CPUs and demanding significantly less energy. Neuromorphic systems consisting of such NPUs and offering a total of 100 million neurons are anticipated in 2020. NPUs were envisioned to accelerate machine learning, and designing neuromorphic algorithms to leverage the benefits of NPUs in other domains remains an open challenge. We design and analyze neuromorphic graph algorithms, focusing on shortest path problems. Our neuromorphic algorithms are packet-passing algorithms relying on data movement for computation, and we develop data-movement lower bounds for conventional algorithms. A fair and rigorous comparison with conventional algorithms and architectures is paramount, and we prove a polynomial-factor advantage even when we assume an NPU with a simple grid-like network of neurons. To the best of our knowledge, this is one of the first examples of a provable asymptotic computational advantage for neuromorphic computing.

Let G be a directed graph with n vertices and m edges, embedded on a surface S, possibly with boundary, with first Betti number beta. We consider the complexity of finding closed directed walks in G that are either contractible (trivial in homotopy) or bounding (trivial in integer homology) in S. Specifically, we describe algorithms to determine whether G contains a simple contractible cycle in O(n+m) time, or a contractible closed walk in O(n+m) time, or a bounding closed walk in O(beta (n+m)) time. Our algorithms rely on subtle relationships between strong connectivity in G and in the dual graph G^*; our contractible-closed-walk algorithm also relies on a seminal topological result of Hass and Scott. We also prove that detecting simple bounding cycles is NP-hard. We also describe three polynomial-time algorithms to compute shortest contractible closed walks, depending on whether the fundamental group of the surface is free, abelian, or hyperbolic. A key step in our algorithm for hyperbolic surfaces is the construction of a context-free grammar with O(g^2L^2) non-terminals that generates all contractible closed walks of length at most L, and only contractible closed walks, in a system of quads of genus g >= 2. Finally, we show that computing shortest simple contractible cycles, shortest simple bounding cycles, and shortest bounding closed walks are all NP-hard.

We consider the maximum flow problem in directed planar graphs with capacities on both vertices and arcs and with multiple sources and sinks. We present three algorithms when the capacities are integers. The first algorithm runs in O(min{k2 n log n, n log3 n+kn}) time when all capacities are bounded by a constant, where n is the number of vertices in the graph and k is the number of terminals. This algorithm is the first to solve the vertex-disjoint paths problem in near-linear time when k is fixed but larger than 2. The second algorithm runs in O(k5n polylog(nU)) time, where U is the largest finite capacity of a single vertex. Finally, when k = 3, we present an algorithm that runs in O(n log n) time; this algorithm works even when the capacities are arbitrary reals. Our algorithms improve on the fastest previously known algorithms when k is fixed and U is bounded by a polynomial in n. Prior to this result, the fastest algorithms ran in O(n2/log n) time for real capacities, O(n3/2 log n log U) for integer capacities, and Õ(n10/7) for unit capacities, even when k = 3.