Autonomous web agents powered by large language models (LLMs) show strong potential for performing goal-oriented tasks such as information retrieval, report generation, and online transactions.These agents mark a key step toward practical embodied reasoning in open web environments.However, existing approaches remain limited in reasoning depth and efficiency: vanilla linear methods fail at multistep reasoning and lack effective backtracking, while other search strategies are coarse-grained and computationally costly.We introduce Branch-and-Browse, a fine-grained web agent framework that unifies structured reasoningacting, contextual memory, and efficient execution.It (i) employs explicit subtask management with tree-structured exploration for controllable multi-branch reasoning, (ii) bootstraps exploration through efficient web state replay with background reasoning, and (iii) leverages a page action memory to share explored actions within and across sessions.On the WebArena benchmark, Branch-and-Browse achieves a task success rate of 35.8% and reduces execution time by up to 40.4% relative to state-of-the-art methods.These results demonstrate that Branch-and-Browse is a reliable and efficient framework for LLM-based web agents.Code is available at https://github.com/ SymbioticLab/Branch-and-Browse.

Accurate abnormal region detection in medical images is critical for early diagnosis. Unlike supervised and self-supervised methods, unsupervised methods require no annotated training data and generalize well to unseen abnormalities. Such advantages are achieved by detecting abnormal regions from the differences between an input image and a generated pseudo-normal image, which is similar to the input image but excludes abnormal regions. However, existing unsupervised methods often suffer from high false positive rate at test time due to poor pixel-level matching between the normal regions of the input image and the pseudo-normal image. To address this challenge, we propose MatchGen, a novel plug-and-play framework to enhance the detection performance of existing unsupervised methods by optimizing the pseudo-normal image at test time. This generates an optimized pseudo-normal image that accurately matches the normal regions of the input while maintaining a clear distinction from the abnormal regions, which significantly improves the detection performance. Extensive experiments on four real-world datasets demonstrate the outstanding effectiveness of MatchGen.

Compared with full client participation, partial client participation is a more practical scenario in federated learning, but it may amplify some challenges in federated learning, such as data heterogeneity. The lack of inactive clients’ updates in partial client participation makes it more likely for the model aggregation to deviate from the aggregation based on full client participation. Training with large batches on individual clients is proposed to address data heterogeneity in general, but their effectiveness under partial client participation is not clear. Motivated by these challenges, we propose to develop a novel federated learning framework, referred to as FedAMD, for partial client participation. The core idea is anchor sampling, which separates partial participants into anchor and miner groups. Each client in the anchor group aims at the local bullseye with the gradient computation using a large batch. Guided by the bullseyes, clients in the miner group steer multiple near-optimal local updates using small batches and update the global model. By integrating the results of the two groups, FedAMD is able to accelerate the training process and improve the model performance. Measured by $\epsilon$-approximation and compared to the state-of-the-art methods, FedAMD achieves the convergence by up to $O(1/\epsilon)$ fewer communication rounds under non-convex objectives. Empirical studies on real-world datasets validate the effectiveness of FedAMD and demonstrate the superiority of the proposed algorithm: Not only does it considerably save computation and communication costs, but also the test accuracy significantly improves.

Traditional one-bit compressed stochastic gradient descent can not be directly employed in multi-hop all-reduce, a widely adopted distributed training paradigm in network-intensive high-performance computing systems such as public clouds. According to our theoretical findings, due to the cascading compression, the training process has considerable deterioration on the convergence performance. To overcome this limitation, we implement a sign-bit compression-based learning synchronization framework, Marsit. It prevents cascading compression via an elaborate bit-wise operation for unbiased sign aggregation and its specific global compensation mechanism for mitigating compression deviation. The proposed framework retains the same theoretical convergence rate as non-compression mechanisms. Experimental results demonstrate that Marsit reduces up to 35% training time while preserving the same accuracy as training without compression.