arXiv subjects

Mengfei Xie

Publications and source records attributed to Mengfei Xie.

5 recordsLinked to original sources

arXiv2025

SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models

Evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer workflows. Existing benchmarks often focus on algorithmic problems or Python-centric bug fixing, leaving critical dimensions of software engineering underexplored. To address these gaps, we introduce SWE-Compass1, a comprehensive benchmark that unifies heterogeneous code-related evaluations into a structured and production-aligned framework. SWE-Compass spans 8 task types, 8 programming scenarios, and 10 programming languages, with 2000 high-quality instances curated from authentic GitHub pull requests and refined through systematic filtering and validation. We benchmark ten state-of-the-art LLMs under two agentic frameworks, SWE-Agent and Claude Code, revealing a clear hierarchy of difficulty across task types, languages, and scenarios. Moreover, by aligning evaluation with real-world developer practices, SWE-Compass provides a rigorous and reproducible foundation for diagnosing and advancing agentic coding capabilities in large language models.

cs.SE↗

arXiv2025

KAT-Coder Technical Report

Recent advances in large language models (LLMs) have enabled progress in agentic coding, where models autonomously reason, plan, and act within interactive software development workflows. However, bridging the gap between static text-based training and dynamic real-world agentic execution remains a core challenge. In this technical report, we present KAT-Coder, a large-scale agentic code model trained through a multi-stage curriculum encompassing Mid-Term Training, Supervised Fine-Tuning (SFT), Reinforcement Fine-Tuning (RFT), and Reinforcement-to-Deployment Adaptation. The Mid-Term stage enhances reasoning, planning, and reflection capabilities through a corpus of real software engineering data and synthetic agentic interactions. The SFT stage constructs a million-sample dataset balancing twenty programming languages, ten development contexts, and ten task archetypes. The RFT stage introduces a novel multi-ground-truth reward formulation for stable and sample-efficient policy optimization. Finally, the Reinforcement-to-Deployment phase adapts the model to production-grade IDE environments using Error-Masked SFT and Tree-Structured Trajectory Training. In summary, these stages enable KAT-Coder to achieve robust tool-use reliability, instruction alignment, and long-context reasoning, forming a deployable foundation for real-world intelligent coding agents. Our KAT series 32B model, KAT-Dev, has been open-sourced on https://huggingface.co/Kwaipilot/KAT-Dev.

cs.CL↗

arXiv2025

Beyond Tag Collision: Cluster-based Memory Management for Tag-based Sanitizers

Tag-based sanitizers attach a small "key" to each pointer and a matching "lock" tag to its target memory object, enabling runtime verification of pointer-object consistency and helping developers to detect potential memory violations. However, the limited tag encoding space challenges existing studies in assigning distinct tags to memory objects across temporal and spatial dimensions, leading to potential tag collisions. In this paper, we present ClusterTag, a novel cluster-based memory allocator aimed at simultaneously mitigating tag collisions in both temporal and spatial dimensions. The core design of ClusterTag effectively balances the significant mismatch between tag encoding space and memory objects: it divides memory objects into multiple independent clusters, thereby limiting tag collisions to finite chunks within each cluster. To mitigate tag collisions across clusters, we design a cluster-grained heap randomization scheme. This approach introduces random address intervals between clusters and further breaks the entropy limitation of the tag space. ClusterTag has been implemented as an independent memory allocator that seamlessly integrates with tag-based sanitizers such as HWASan, and maintains comparable performance overhead (within 1%) at various randomization densities. Security evaluations on the Juliet dataset indicate that ClusterTag exhibits deterministic results across 500 repeated tests (5,652 reported and 1,530 missed), while the existing three types of tag assignment strategies all exhibit probabilistic false negatives due to tag collisions. Quantitative analysis across three tag collision distance metrics-minimum, average, and unpredictability-demonstrates that ClusterTag achieves balanced improvements across all three, whereas prior tag assignment schemes (random, staggered, fixed) show significant trade-offs in at least one metric.

cs.CR↗

arXiv2025

SeamlessFlow: A Trainer Agent Isolation RL Framework Achieving Bubble-Free Pipelines via Tag Scheduling

We introduce SeamlessFlow, a server based reinforcement learning (RL) framework that addresses two core challenges in industrial scale RL: (1) decoupling RL training from the complex execution flow of agents; (2) maximizing GPU utilization with minimal idle time while preserving the stability and scalability required for large-scale deployments. First, SeamlessFlow introduces a data plane that decouples the RL trainer from diverse, complex agent implementations while sustaining high throughput. A central trajectory manager maintains complete interaction histories and supports partial rollout, allowing rollout to pause for weight updates and resume seamlessly, keeping agents unaware of service interruptions. Second, we propose a tag driven scheduling paradigm that abstracts hardware into capability tagged resources, unifying colocated and disaggregated architectures. Based on this, SeamlessFlow introduces a spatiotemporal multiplexing pipeline that dynamically reassigns idle training nodes to rollout in a train rollout separated setup, eliminating pipeline bubbles and fully exploiting heterogeneous cluster resources. By combining these innovations, SeamlessFlow delivers both stability and high performance, making it well suited for multi agent, long horizon, and other complex RL tasks.

cs.LG↗

arXiv2024

Retrofitting XoM for Stripped Binaries without Embedded Data Relocation

In this paper, we present PXoM, a practical technique to seamlessly retrofit XoM into stripped binaries on the x86-64 platform. As handling the mixture of code and data is a well-known challenge for XoM, most existing methods require the strict separation of code and data areas via either compile-time transformation or binary patching, so that the unreadable permission can be safely enforced at the granularity of memory pages. In contrast to previous approaches, we provide a fine-grained memory permission control mechanism to restrict the read permission of code while allowing legitimate data reads within code pages. This novelty enables PXoM to harden stripped binaries but without resorting to error-prone embedded data relocation. We leverage Intel's hardware feature, Memory Protection Keys, to offer an efficient fine-grained permission control. We measure PXoM's performance with both micro- and macro-benchmarks, and it only introduces negligible runtime overhead. Our security evaluation shows that PXoM leaves adversaries with little wiggle room to harvest all of the required gadgets, suggesting PXoM is practical for real-world deployment.

cs.CR↗