Large language models (LLMs) for code editing have achieved remarkable progress, yet recent empirical studies reveal a fundamental disconnect between technical accuracy and developer productivity . Despite their strong benchmark performance, developers complete tasks 19% slower when using AI assistance, with over 68.81% of recommendations disrupting their mental flow. This misalignment stems from the use of static commit snapshots that lack temporal information, causing models to optimize for end results rather than the incremental, context-sensitive steps that align with developers’ natural reasoning process. To bridge this gap, we present EditFlow , which benchmarks and optimizes subsequent code edit recommendation systems through the reconstruction of developer editing flows. EditFlow addresses three key challenges. First, collecting edit-order data that reflects developers’ flow is inherently difficult: manual annotation introduces prohibitive overhead, while development logs capture only single trajectories instead of all plausible editing flows. Second, benchmarking recommendation performance against developers’ ongoing editing flow requires a digital-twin-like simulation that can faithfully simulate the editing process. Third, existing heterogeneous systems vary drastically in scale and architecture, posing challenges for developing a unified optimization strategy that endows all models with mental-flow awareness regardless of design or capability. To overcome these challenges, we propose three tightly coupled components: (1) a prompt auto-tuning mechanism that learns an optimized prompt for inferring the relative order between two edits, (2) a digital twin that replays reconstructed edit sequences to simulate developers’ editing process, and (3) EditFlow , a unified optimization strategy that optimizes the flow continuity of subsequent edit suggestions based on developers’ ongoing flow. Evaluations across diverse benchmarks, including manually annotated commits, real-world industrial code, and open-source repositories, show that EditFlow improves order reconstruction accuracy by 63.81%, reduces flow violations by over 75%, and boosts recommendation precision by 66.99%. A user study with 32 developers further demonstrates 25.11% faster task completion and significantly higher perceived recommendation quality. To the best of our knowledge, EditFlow is the first to evaluate and optimize code edit recommendation systems from the perspective of developers’ mental flow, establishing flow-awareness as a new dimension for advancing human-AI code collaboration.

In industrial and open-source software engineering tasks, developers often perform project-wise code editing tasks, including feature enhancement, refactoring, and bug fixing, where the leading AI models are expected to support the productivity. Hence, researchers and practitioners have proposed and adopted many LLM-based solutions to facilitate their real-world development. However, they largely suffer from the balance among predicting scope, accuracy, and efficiency. For example, solutions like Cursor achieve high accuracy only in a local editing scope while its performance drops on cross-file edits. In contrast, solutions like CoEdPilot exhibit efficiency limitations when used to predict project-wise edits.In this work, we propose TRACE (Tool-integrated RecommendAtion for Code Editing), a novel subsequent code editing solution to push the boundary of scope, accuracy, and efficiency. Our rationale lies in that code edits are triggered for either semantic or syntactic reasons. Therefore, TRACE predicts subsequent edits by interleaving neural-based induction for semantic edit prediction and tool-based deduction for syntactic edit prediction. The tools can be any IDE facilities, such as refactoring tools (e.g., rename) or linting tools (e.g., use-def), providing decent performance of deducing edit-location and edit-generation. Technically, we address the challenge of (1) when to interleave between neural-based and tool-based prediction and (2) how to further improve the performance of neural-based prediction. As for the former, we learn a neural model to detect when to invoke IDE editing tools. As for the latter, we propose a novel and fine-grained editing representation to further boost the performance of neural editing models.Our extensive experiments show that, in comparison to the state-of-the-arts such as CoEdPilot, GrACE, and CCT5, TRACE significantly improves the performance of edit location (by 43.76%) and edit generation (by 11.16%). Our simulation experiment on an interactive editing setting shows that TRACE achieves an acceptance rate 6.15% higher than Cursor. Moreover, our user study consists of 24 participants on Cursor, CoEdPilot, and TRACE, on three code editing tasks. The results show that the experimental group with TRACE achieves leading performance on cross-file global edits. In addition, we observe concerning user behaviours on how participants deal with false predictions by the tools, shedding light on the design of future code-editing tools.

Edge computing, a recently developed computing paradigm, seeks to extend cloud computing by providing users minimal latency. In a mobile edge computing (MEC) environment, edge servers are placed close to edge users to offer computing resources, and the coverage of adjacent edge servers may partially overlap. Because of the restricted resource and coverage of each edge server, edge user allocation (EUA), i.e., determining the optimal way to allocate users to different servers in the overlapping area, has emerged as a major challenge in edge computing. Despite the NP-hardness of obtaining an optimal solution, it is possible to evaluate the quality of a solution in a short amount of time with given metrics. Consequently, deep reinforcement learning (DRL) can be used to solve EUA by attempting numerous allocations and optimizing the allocation strategy depending on the rewards of those allocations. In this study, we propose the Dual-sequence Attention Model (DSAM) as the DRL agent, which encodes users using self-attention mechanisms and directly outputs the probability of matching between users and servers using an attention-based pointer mechanism, enabling the selection of the most suitable server for each user. Experimental results show that our method outperforms the baseline approaches in terms of allocated users, required servers, and resource utilization, and its running speed meets real-time requirements.