Searcharxiv⌕ Search

arXiv subjects

Yuchi Ma

Publications and source records attributed to Yuchi Ma.

At least 19 recordsLinked to original sources

From Conversation to Evaluation: Benchmarking LLMs on Development Knowledge via SimpleDevQA

The Development Knowledge Question Answering (Dev Knowledge QA) task aims to provide accurate natural language answers to knowledge-seeking questions during software development. To investigate the importance of Dev Knowledge QA in AI-assisted software development and the extent to which it has been explored, we conduct a preliminary analysis of real user-LLM dialogues from WildChat. Our findings indicate that Dev Knowledge QA plays a significant role in real-world software development scenarios, and these raw dialogues cannot be directly used to construct a Dev Knowledge QA benchmark. Existing Dev Knowledge QA benchmarks are limited in development knowledge scope and often not built from real user queries. To bridge this gap, we design a three-phase pipeline that transforms real-world dialogue into simple development knowledge-seeking QA pairs. Through this pipeline, we introduce SimpleDevQA, a multilingual Dev Knowledge QA benchmark inspired by real user dialogues. This dataset covers three languages (English, Chinese, and Russian), and focuses on questions with unique, short, and verifiable answers, making evaluation more accurate and simple. Extensive experiments with 21 mainstream LLMs show that closed-source models generally perform best on SimpleDevQA. We also find that RAG-based knowledge injection improves accuracy, and that Dev Knowledge QA performance correlates with both model confidence and code-generation capability. To facilitate the replication study, we have released our data and code at: https://github.com/DeepSoftwareAnalytics/SimpleDevQA.

cs.SE↗

Earth Embeddings in Environmental Remote Sensing

Earth observations from satellite platforms have profoundly transformed research and applications across numerous domains. However, uneven observation coverage and frequent data gaps continue to limit their ability to capture Earth's surface dynamics. Moreover, processing multi-modal Earth observations requires substantial computational resources and sophisticated data harmonization frameworks, which may not be readily accessible to many remote sensing practitioners. Earth embeddings have emerged as promising solutions to these challenges. As general-purpose representations converted from multi-source Earth observations, Earth embeddings can support a wide range of downstream tasks with no requirement of task-specific feature design and preprocessing. In this study, we first introduce the theoretical foundations of Earth embeddings. Then, we review several representative Earth embedding products. We next examine the applications of Earth embeddings across six major domains of environmental remote sensing. Finally, we systematically assess the performance of Earth embeddings in four downstream tasks, including hyperspectral image classification, individual tree crown segmentation, crop yield prediction, and aboveground biomass mapping. Our review and case studies suggest that, despite several advantages over conventional Earth observation data, current Earth embeddings do not always outperform remote sensing imagery or hand-crafted features. Earth embeddings should not be viewed as a direct replacement for conventional EO data, but rather as representations that provide stable information across space and time. Remote sensing practitioners may consider evaluating Earth embeddings' suitability for specific tasks and using them strategically, rather than assuming superior performance by default.

cs.AI↗

Simple Test-Time Refinement for Plot-to-Code Generation via Visual-Code Diagnostics

Plot-to-code generation has been greatly advanced by recent multimodal large language models (MLLMs). However, existing studies mainly focus on one-pass generation or iterative sampling guided by verifier-based filtering, which does not align with the typical human programming workflow of generate first, then iteratively error-location and fix. This naturally motivates a test-time refinement paradigm for plot-to-code generation. In this work, we present the first study on plot-to-code generation via iterative test-time refinement. We propose a Visual-Code Diagnostics framework that enables refinement through visual feedback from source code. Specifically, we first categorize generation errors into four coarse-grained types, and then train lightweight discriminators to recognize and localize these errors based on the rendered visual outputs and corresponding code. Unlike traditional compiler- or debugger-based verification, our approach performs iterative refinement guided by one diagnostics system, enabling more effective semantic and visual correction during test time. Extensive experiments demonstrate that our method consistently improves generation quality across diverse generators and significantly outperforms strong test-time scaling baselines.

cs.CL↗

ASTOR: Multi-Task Code Reinforcement Learning via Utility-Driven Coordination

Reinforcement learning (RL) with verifiable rewards has proven effective at post-training LLMs for coding, yet deploying separate task-specific specialists incurs costs that scale with the number of tasks, motivating a unified multi-task RL (MTRL) approach. However, existing MTRL methods treat all coding tasks uniformly, relying on fixed data curricula under a shared optimization strategy, ultimately limiting the effectiveness of multi-task training. To address these limitations, we propose ASTOR, a multi-tASk code reinforcement learning framework via uTility-driven coORdination. Centered on task utility, a signal capturing each task learning potential and cross-task synergy, ASTOR comprises two coupled modules: 1) Hierarchical Utility-Routed Data Scheduling module hierarchically allocates training budget and prioritizes informative prompts, steering training toward the most valuable data and 2) Adaptive Utility-Calibrated Policy Optimization module dynamically scales per-task KL regularization, matching update constraints to each tasks current training state. Experiments on two widely-used LLMs across four representative coding tasks demonstrate that ASTOR consistently improves a single model across all tasks, outperforming the best task-specific specialist by 9.0%-9.5% and surpassing the strongest MTRL baseline by 7.5%-12.8%.

cs.SE↗

Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation

The repository-level code generation task requires synthesizing code that satisfies task requirements while remaining consistent with the target repository context. Since real-world repositories often exceed the input length limits of LLMs, existing approaches commonly adopt retrieval-augmented generation (RAG) to provide repository-specific context. Despite improving repository-context retrieval, existing methods typically provide context as task-level support, without explicitly identifying the critical tokens that require fine-grained repository context during generation. During the autoregressive generation process of LLMs, errors often concentrate at a small number of decisive positions: once such tokens are generated incorrectly, subsequent code may follow an incorrect semantic path and eventually lead to functional failure. We refer to these positions as "critical tokens". In this paper, we propose ACToR, an adaptive critical token-aware retrieval framework for repository-level code generation. ACToR identifies critical tokens during generation and triggers targeted retrieval on demand to provide repository context at these decisive positions. In addition, we design a position-aware weighting method for dense retrievers to prioritize context that is more informative for generation. We evaluate ACToR on two representative repository-level benchmarks, RepoExec and CoderEval. Experimental results show that ACToR consistently outperforms state-of-the-art methods, achieving relative improvements of 8.4% on RepoExec and 15.4% on CoderEval. Beyond performance gains, we systematically quantify the impact of critical tokens, revealing their central role in major generation failures and highlighting the necessity of targeted retrieval strategies. We provide the code and data at https://github.com/DeepSoftwareAnalytics/ACToR.

cs.SE↗

Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation

Evaluating software engineering agents on realistic benchmarks is costly, since each task may require multi-step code exploration, modification, and test execution. Existing efficient evaluation methods select representative subsets to estimate full-benchmark performance, but are largely result-only: they fit historical pass/fail response matrices or static task semantics, discarding how agents solve problems. We propose PTA-IRT, a Privileged Trajectory-Aware Item Response Theory framework that fuses process and outcome signals. Historical execution trajectories supply process-level evidence beyond pass/fail, such as explored context, attempted edits, and solving paths, which PTA-IRT uses as privileged information for calibration subset selection and ability estimation. Under low calibration budgets, PTA-IRT consistently outperforms prior IRT baselines on score and ranking recovery across four SWE benchmarks. Code and data are publicly available at https://github.com/DeepSoftwareAnalytics/PTA-IRT.

cs.SE↗

From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench

In real-world software development, code review typically involves iterative interactions between developers and reviewers to improve software quality, making the process costly and time-consuming. Although recent work explores large language models (LLMs) for automated code review, most approaches oversimplify code review into a single-round, static decision task, which fails to capture the multi-round interactive nature and the complex problem-solving processes inherent in realistic review scenarios. To bridge this gap, we introduce MCR-Bench, the first defect state-aware benchmark designed for realistic multi-round code review. MCR-Bench covers five commonly-used programming languages and consists of 2,269 real-world multi-round code review tasks, each of which is annotated with fine-grained defect information and cross-round state labels. Each task in MCR-Bench is equipped with fine-grained defect metadata (e.g., description, type, severity) alongside dynamic state annotations, capturing the complete evolutionary trajectory of a defect throughout the multi-round process. We obtain several findings through extensive experiments on MCR-Bench with mainstream LLMs. (1) Limited overall capability: experiments reveal that mainstream LLMs exhibit limited overall performance in defect detection and defect lifecycle state tracking, with performance degrading significantly as the number of interaction rounds increases; (2) Defect-sensitive performance: LLMs' performance varies substantially across different defect types and severity levels, with semantically complex or low-salience defects being significantly more likely to be missed; (3) Underlying Failure Mechanisms: our in-depth error analysis dissects the distinct drivers of false positives and false negatives, revealing critical weaknesses such as cross-round temporal misalignment and inadequate long-range memory.

cs.SE↗

SWE-Prime: Fewer Trajectories, Better Performance

To improve large language models' ability to resolve real-world software issues, prior work has focused on constructing large-scale agent trajectory datasets and performing supervised fine-tuning (SFT) on successful trajectories. However, task success does not guarantee high-quality supervision: successful trajectories may still contain ineffective, redundant, or risky steps. Directly using such trajectories for SFT can introduce noisy supervision and encourage models to imitate undesirable problem-solving behaviors. Therefore, we propose SWE-Prime, a multi-granularity, two-stage SFT data selection method that progressively filters training data at the trajectory and segment levels. Specifically, the first stage performs trajectory-level screening based on process quality, result quality, and data representativeness, selecting a high-quality and representative subset of successful trajectories. The second stage performs segment-level selection by grouping consecutive steps into semantic segments and assessing each segment based on its contribution to the final solution, learnability, and potential risks. During SFT, all segments remain in the sequence to preserve context, while only selected segments contribute to the loss computation. Experiments on SWE-Bench Pro and SWE-Bench Verified show that training on the 10% trajectory subset selected by SWE-Prime outperforms training on the full resolved dataset, yielding relative performance gains of up to 12.2% and 24.2%, respectively.

cs.SE↗

Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework

Memory emerges as the core module in the large language model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), where memory can enable knowledge accumulation, iterative reasoning and self-evolution. A number of memory methods have been proposed in the literature. However, these methods have not been systematically and comprehensively compared under the same experimental settings. In this paper, we first summarize a unified framework that covers existing representative agent memory methods from a high-level perspective. We then extensively compare representative agent memory methods on two long-term conversational benchmarks and an agentic memory benchmark, and examine the effectiveness of representative methods, providing a thorough analysis of those methods. As a byproduct of our experimental analysis, we also design a new memory method by exploiting modules in the existing methods, which outperforms the state-of-the-art methods. Finally, based on these findings, we offer promising future research opportunities. We believe that a deeper understanding of the behavior of existing methods can provide valuable new insights for future research.

cs.CL↗

PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents

While Large Language Models have greatly advanced automated issue resolution, existing agent-based methods exhibit a fundamental limitation in their insufficient exploration of repair strategies. This insufficiency manifests in two key aspects. First, the exploration of multiple potential edit locations is limited. Second, the exploration of repair attempts at each location is also insufficient. To address these challenges, we present PhoenixRepair, a multi-agent framework that systematically explores multiple candidate edit locations and performs iterative reflection and refinement on patch generation, thereby expanding the search space of repair strategies. Our framework begins with multi-location sampling, optionally augmented with graph-based localization information for difficult tasks, followed by iterative reflection and refinement to generate better patches, culminating in final-round generation guided by distilled insights from all historical attempts. Experiments on SWE-bench-Verified demonstrate that PhoenixRepair achieves the largest relative improvement of 7.8\% over SWE-agent under DeepSeek-V3.1, and attains the highest resolved rate of 76.0\% Pass@1 under MiniMax-M2.5. Meanwhile, it achieves higher fault localization accuracy than existing approaches. Our code is available at https://github.com/DeepSoftwareAnalytics/PhoenixRepair.

cs.AI↗

AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion

Repository-level code completion remains a challenging task for existing code large language models (code LLMs) due to their limited understanding of repository-specific context and domain knowledge. While retrieval-augmented generation (RAG) approaches have shown promise by retrieving relevant code snippets as cross-file context, they suffer from two fundamental problems: misalignment between the query and the target code in the retrieval process, and the inability of existing retrieval methods to effectively utilize the inference information. To address these challenges, we propose AlignCoder, a repository-level code completion framework that introduces a query enhancement mechanism and a reinforcement learning based retriever training method. Our approach generates multiple candidate completions to construct an enhanced query that bridges the semantic gap between the initial query and the target code. Additionally, we employ reinforcement learning to train an AlignRetriever that learns to leverage inference information in the enhanced query for more accurate retrieval. We evaluate AlignCoder on two widely-used benchmarks (CrossCodeEval and RepoEval) across five backbone code LLMs, demonstrating an 18.1% improvement in EM score compared to baselines on the CrossCodeEval benchmark. The results show that our framework achieves superior performance and exhibits high generalizability across various code LLMs and programming languages.

cs.SE↗

H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure

Memory data are ubiquitous in Large Language Model (LLM)-based agents (e.g., OpenClaw and Manus). A few recent works have attempted to exploit agents'memory for improving their performance on the question-answering (QA) task, but they lack a principled mechanism for effectively modeling how memory data evolves over time and retrieving memory data effectively, leading to poor performance in memory utilization. To fill this gap, we present H-Mem, a novel memory mechanism via a hybrid structure that can not only effectively model the evolution of agent memory over a long period of time, but also provide an efficient memory retrieval approach. Particularly, H-Mem builds a temporal and semantic tree structure that allows the short-term memory data to evolve progressively into long-term memory data, where the latter provides summarized information about the former, while simultaneously constructing a knowledge graph to capture the relationships between entities in memory. Moreover, it offers an effective memory retrieval approach by exploiting the hybrid structure of the tree and graph structures. Extensive experiments on three agent memory benchmarks show that H-Mem achieves state-of-the-art performance on the QA task.

cs.CL↗

ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models (LLMs) for solving question-answer (QA) tasks. The state-of-the-art RAG approaches often use the graph data as the external data since they capture the rich semantic information and link relationships between entities. However, existing graph-based RAG approaches cannot accurately identify the relevant information from the graph and also consume large numbers of tokens in the online retrieval process. To address these issues, we introduce a novel graph-based RAG approach, called Attributed Community-based Hierarchical RAG (ArchRAG), by augmenting the question using attributed communities, and also introducing a novel LLM-based hierarchical clustering method. To retrieve the most relevant information from the graph for the question, we build a novel hierarchical index structure for the attributed communities and develop an effective online retrieval method. Experimental results demonstrate that ArchRAG outperforms existing methods in both accuracy and token cost.

cs.IR↗

In-depth Analysis of Graph-based RAG in a Unified Framework

Graph-based Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models (LLMs), improving their factual accuracy, adaptability, interpretability, and trustworthiness. A number of graph-based RAG methods have been proposed in the literature. However, these methods have not been systematically and comprehensively compared under the same experimental settings. In this paper, we first summarize a unified framework to incorporate all graph-based RAG methods from a high-level perspective. We then extensively compare representative graph-based RAG methods over a range of questing-answering (QA) datasets -- from specific questions to abstract questions -- and examine the effectiveness of all methods, providing a thorough analysis of graph-based RAG approaches. As a byproduct of our experimental analysis, we are also able to identify new variants of the graph-based RAG methods over specific QA and abstract QA tasks respectively, by combining existing techniques, which outperform the state-of-the-art methods. Finally, based on these findings, we offer promising research opportunities. We believe that a deeper understanding of the behavior of existing methods can provide new valuable insights for future research.

cs.IR↗

Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMs

Training effective software engineering agents requires large volumes of task-specific trajectories, incurring substantial data construction costs. Inspired by the "Less-Is-More" hypothesis in mathematical reasoning, we investigate its extension to agentic scenarios and propose an end-to-end training framework that achieves superior agentic capabilities with fewer but higher-quality training trajectories. This is achieved via STITCH (Sliding-memory Trajectory Inference and Task Chunking Heuristic), a coarse-to-fine mechanism that filters low-value noise and retains decision-critical tokens to maximize training signal quality. We conduct experiments across multiple agent frameworks (e.g., mini-SWE-agent, MSWE-agent), model scales (30B to 355B), and multilingual settings (Python, Java, and ArkTS). On SWE-bench Verified, models trained with STITCH achieve up to 63.16% relative improvement over base models. On Multi-SWE-bench (Java), MiniMax-M2.5-STITCH achieves 43.75% with our CodeArts Agent scaffold (+16.67%). On HarmonyOS (ArkTS), GLM-4.7-STITCH improves the compilation pass rate to 61.31% (+43.34%) with less than 1K training trajectories. Our results confirm that the "Less-Is-More" paradigm generalizes effectively to complex agentic tasks across diverse languages and model scales.

cs.SE↗

Towards an Understanding of Context Utilization in Code Intelligence

Code intelligence is an emerging domain in software engineering, aiming to improve the effectiveness and efficiency of various code-related tasks. Recent research suggests that incorporating contextual information beyond the basic original task inputs (i.e., source code) can substantially enhance model performance. Such contextual signals may be obtained directly or indirectly from sources such as API documentation or intermediate representations like abstract syntax trees can significantly improve the effectiveness of code intelligence. Despite growing academic interest, there is a lack of systematic analysis of context in code intelligence. To address this gap, we conduct an extensive literature review of 146 relevant studies published between September 2007 and August 2024. Our investigation yields four main contributions. (1) A quantitative analysis of the research landscape, including publication trends, venues, and the explored domains; (2) A novel taxonomy of context types used in code intelligence; (3) A task-oriented analysis investigating context integration strategies across diverse code intelligence tasks; (4) A critical evaluation of evaluation methodologies for context-aware methods. Based on these findings, we identify fundamental challenges in context utilization in current code intelligence systems and propose a research roadmap that outlines key opportunities for future research.

cs.SE↗

DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning

Large language models (LLMs) have demonstrated impressive capabilities in code generation by leveraging retrieval-augmented generation (RAG) methods. However, the computational costs associated with LLM inference, particularly in terms of latency and energy consumption, have received limited attention in the security context. This paper introduces DrainCode, the first adversarial attack targeting the computational efficiency of RAG-based code generation systems. By strategically poisoning retrieval contexts through a mutation-based approach, DrainCode forces LLMs to produce significantly longer outputs, thereby increasing GPU latency and energy consumption. We evaluate the effectiveness of DrainCode across multiple models. Our experiments show that DrainCode achieves up to an 85% increase in latency, a 49% increase in energy consumption, and more than a 3x increase in output length compared to the baseline. Furthermore, we demonstrate the generalizability of the attack across different prompting strategies and its effectiveness compared to different defenses. The results highlight DrainCode as a potential method for increasing the computational overhead of LLMs, making it useful for evaluating LLM security in resource-constrained environments. We provide code and data at https://github.com/DeepSoftwareAnalytics/DrainCode.

cs.SE↗

Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code

The rise of Large Language Models (LLMs) has significantly advanced various applications on software engineering tasks, particularly in code generation. Despite the promising performance, LLMs are prone to generate hallucinations, which means LLMs might produce outputs that deviate from users' intent, exhibit internal inconsistencies, or misaligned with the real-world knowledge, making the deployment of LLMs potentially risky in a wide range of applications. Existing work mainly focuses on investigating the hallucination in the domain of Natural Language Generation (NLG), leaving a gap in comprehensively understanding the types, causes, and impacts of hallucinations in the context of code generation. To bridge the gap, we conducted a thematic analysis of the LLM-generated code to summarize and categorize the hallucinations, as well as their causes and impacts. Our study established a comprehensive taxonomy of code hallucinations, encompassing 3 primary categories and 12 specific categories. Furthermore, we systematically analyzed the distribution of hallucinations, exploring variations among different LLMs and benchmarks. Moreover, we perform an in-depth analysis on the causes and impacts of various hallucinations, aiming to provide valuable insights into hallucination mitigation. Finally, to enhance the correctness and reliability of LLM-generated code in a lightweight manner, we explore training-free hallucination mitigation approaches by prompt enhancing techniques. We believe our findings will shed light on future research about code hallucination evaluation and mitigation, ultimately paving the way for building more effective and reliable code LLMs in the future. The replication package is available at https://github.com/Lorien1128/code_hallucination

cs.SE↗