Yuchi Ma

Yanlin Wang, Wanjun Zhong, Yanxian Huang et al.

In recent years, Large Language Models (LLMs) have achieved remarkable success and have been widely used in various downstream tasks, especially in the tasks of the software engineering (SE) field. We find that many studies combining LLMs with SE have employed the concept of agents either explicitly or implicitly. However, there is a lack of an in-depth survey to sort out the development context of existing works, analyze how existing works combine the LLM-based agent technologies to optimize various tasks, and clarify the framework of LLM-based agents in SE. In this paper, we conduct the first survey of the studies on combining LLM-based agents with SE and present a framework of LLM-based agents in SE which includes three key modules: perception, memory, and action. We also summarize the current challenges in combining the two fields and propose future opportunities in response to existing challenges. We maintain a GitHub repository of the related papers at: https://github.com/DeepSoftwareAnalytics/Awesome-Agent4SE.

Fenia Christopoulou, Gerasimos Lampouras, Milan Gritta et al.

We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i.e. the synthesis of programming language solutions given a natural language problem description. We train PanGu-Coder using a two-stage strategy: the first stage employs Causal Language Modelling (CLM) to pre-train on raw programming language data, while the second stage uses a combination of Causal Language Modelling and Masked Language Modelling (MLM) training objectives that focus on the downstream task of text-to-code generation and train on loosely curated pairs of natural language program definitions and code functions. Finally, we discuss PanGu-Coder-FT, which is fine-tuned on a combination of competitive programming problems and code with continuous integration tests. We evaluate PanGu-Coder with a focus on whether it generates functionally correct programs and demonstrate that it achieves equivalent or better performance than similarly sized models, such as CodeX, while attending a smaller context window and training on less data.

Gengchen Mai, Ni Lao, Weiwei Sun et al.

Existing digital sensors capture images at fixed spatial and spectral resolutions (e.g., RGB, multispectral, and hyperspectral images), and each combination requires bespoke machine learning models. Neural Implicit Functions partially overcome the spatial resolution challenge by representing an image in a resolution-independent way. However, they still operate at fixed, pre-defined spectral resolutions. To address this challenge, we propose Spatial-Spectral Implicit Function (SSIF), a neural implicit model that represents an image as a function of both continuous pixel coordinates in the spatial domain and continuous wavelengths in the spectral domain. We empirically demonstrate the effectiveness of SSIF on two challenging spatio-spectral super-resolution benchmarks. We observe that SSIF consistently outperforms state-of-the-art baselines even when the baselines are allowed to train separate models at each spectral resolution. We show that SSIF generalizes well to both unseen spatial resolutions and spectral resolutions. Moreover, SSIF can generate high-resolution images that improve the performance of downstream tasks (e.g., land use classification) by 1.7%-7%.

Zeyu Cao, Yuchi Ma, Zhou Zhang

In the U.S., corn is the most produced crop and has been an essential part of the American diet. To meet the demand for supply chain management and regional food security, accurate and timely large-scale corn yield prediction is attracting more attention in precision agriculture. Recently, remote sensing technology and machine learning methods have been widely explored for crop yield prediction. Currently, most county-level yield prediction models use county-level mean variables for prediction, ignoring much detailed information. Moreover, inconsistent spatial resolution between crop area and satellite sensors results in mixed pixels, which may decrease the prediction accuracy. Only a few works have addressed the mixed pixels problem in large-scale crop yield prediction. To address the information loss and mixed pixels problem, we developed a variational autoencoder (VAE) based multiple instance regression (MIR) model for large-scaled corn yield prediction. We use all unlabeled data to train a VAE and the well-trained VAE for anomaly detection. As a preprocess method, anomaly detection can help MIR find a better representation of every bag than traditional MIR methods, thus better performing in large-scale corn yield prediction. Our experiments showed that variational autoencoder based multiple instance regression (VAEMIR) outperformed all baseline methods in large-scale corn yield prediction. Though a suitable meta parameter is required, VAEMIR shows excellent potential in feature learning and extraction for large-scale corn yield prediction.

Sicong Liu, Yanxian Huang, Mingwei Liu et al.

Code generation tasks aim to automate the conversion of user requirements into executable code, significantly reducing manual development efforts and enhancing software productivity. The emergence of large language models (LLMs) has significantly advanced code generation, though their efficiency is still impacted by certain inherent architectural constraints. Each token generation necessitates a complete inference pass, requiring persistent retention of contextual information in memory and escalating resource consumption. While existing research prioritizes inference-phase optimizations such as prompt compression and model quantization, the generation phase remains underexplored. To tackle these challenges, we propose a knowledge-infused framework named ShortCoder, which optimizes code generation efficiency while preserving semantic equivalence and readability. In particular, we introduce: (1) ten syntax-level simplification rules for Python, derived from AST-preserving transformations, achieving 18.1% token reduction without functional compromise; (2) a hybrid data synthesis pipeline integrating rule-based rewriting with LLM-guided refinement, producing ShorterCodeBench, a corpus of validated tuples of original code and simplified code with semantic consistency; (3) a fine-tuning strategy that injects conciseness awareness into the base LLMs. Extensive experimental results demonstrate that ShortCoder consistently outperforms state-of-the-art methods on HumanEval, achieving an improvement of 18.1%-37.8% in generation efficiency over previous methods while ensuring the performance of code generation.

Tianyue Jiang, Yanli Wang, Yanlin Wang et al.

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.

Jiajun Wu, Jian Yang, Wei Zhang et al.

Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, their effectiveness heavily relies on supervised training with extensive labeled (e.g., question-answering pairs) or unlabeled datasets (e.g., code snippets), which are often expensive and difficult to obtain at scale. To address this limitation, this paper introduces a method IPC, an unsupervised framework that leverages Internal Probing of LLMs for Code generation without any external corpus, even unlabeled code snippets. We introduce the problem space probing, test understanding probing, solution space probing, and knowledge consolidation and reinforcement to probe the internal knowledge and confidence patterns existing in LLMs. Further, IPC identifies reliable code candidates through self-consistency mechanisms and representation-based quality estimation to train UCoder (coder with unsupervised learning). We validate the proposed approach across multiple code benchmarks, demonstrating that unsupervised methods can achieve competitive performance compared to supervised approaches while significantly reducing the dependency on labeled data and computational resources. Analytic experiments reveal that internal model states contain rich signals about code quality and correctness, and that properly harnessing these signals enables effective unsupervised learning for code generation tasks, opening new directions for training code LLMs in resource-constrained scenarios.

Yanchen Wu, Tenghui Lin, Yingli Zhou et al.

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 incorporates all the existing agent memory methods from a high-level perspective. We then extensively compare representative agent memory methods on two well-known benchmarks and examine the effectiveness of all 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.

Yuchi Ma, Yawen Shen, Anu Swatantran et al.

Geospatial foundation models (GFMs) have emerged as a promising approach to overcoming the limitations in existing featurization methods. More recently, Google DeepMind has introduced AlphaEarth Foundation (AEF), a GFM pre-trained using multi-source EOs across continuous time. An annual and global embedding dataset is produced using AEF that is ready for analysis and modeling. The internal experiments show that AEF embeddings have outperformed operational models in 15 EO tasks without re-training. However, those experiments are mostly about land cover and land use classification. Applying AEF and other GFMs to agricultural monitoring require an in-depth evaluation in critical agricultural downstream tasks. There is also a lack of comprehensive comparison between the AEF-based models and traditional remote sensing (RS)-based models under different scenarios, which could offer valuable guidance for researchers and practitioners. This study addresses some of these gaps by evaluating AEF embeddings in three agricultural downstream tasks in the U.S., including crop yield prediction, tillage mapping, and cover crop mapping. Datasets are compiled from both public and private sources to comprehensively evaluate AEF embeddings across tasks at different scales and locations, and RS-based models are trained as comparison models. AEF-based models generally exhibit strong performance on all tasks and are competitive with purpose-built RS-based models in yield prediction and county-level tillage mapping when trained on local data. However, we also find several limitations in current AEF embeddings, such as limited spatial transferability compared to RS-based models, low interpretability, and limited time sensitivity. These limitations recommend caution when applying AEF embeddings in agriculture, where time sensitivity, generalizability, and interpretability is important.

Jiawei Yu, Yixiang Fang, Xilin Liu et al.

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.

Dewu Zheng, Yanlin Wang, Ensheng Shi et al.

With the rapid advancement of large language models (LLMs), extensive research has been conducted to investigate the code generation capabilities of LLMs. However, existing efforts primarily focus on general-domain tasks, leaving LLMs' code generation performance in real-world application domains underexplored. This raises a critical question: can a model's general-domain coding ability reliably represent its ability in specialized domains? In this paper, we introduce DomainCodeBench, a multi-domain code generation benchmark designed to systematically evaluate LLMs across 12 software application domains and 15 programming languages. DomainCodeBench contains 2,400 manually verified tasks with ground truth, human-annotated docstrings, and fine-grained dependency information to ensure more coverage of domain-specific challenges. Specifically, we first identify the most popular application domains by topic mining. Then, we curate coding tasks based on commonly used frameworks and platforms in each domain. We obtain several findings through extensive experiments on DomainCodeBench with ten mainstream LLMs. (1) Performance decoupling: experiments reveal that top general-domain models do not consistently excel in specific application domains; (2) Domain-specific weaknesses: LLMs often fail due to domain knowledge gaps and third-party library misusage; (3) Contextual enhancement: we show that augmenting prompts with domain-specific knowledge improves performance by around 38.17%, providing actionable insights for performance optimization. Our replication package, including the benchmark, source code, and experimental results, is available at https://github.com/DeepSoftwareAnalytics/DomainCodeBench.

Fang Liu, Yang Liu, Lin Shi et al.

The rise of Large Language Models (LLMs) has significantly advanced many 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 misalign with the factual knowledge, making the deployment of LLMs potentially risky in a wide range of applications. Existing work mainly focuses on investing the hallucination in the domain of natural language generation (NLG), leaving a gap in understanding the types and extent 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 present in it. Our study established a comprehensive taxonomy of hallucinations in LLM-generated code, encompassing 5 primary categories of hallucinations depending on the conflicting objectives and varying degrees of deviation observed in code generation. Furthermore, we systematically analyzed the distribution of hallucinations, exploring variations among different LLMs and their correlation with code correctness. Based on the results, we proposed HalluCode, a benchmark for evaluating the performance of code LLMs in recognizing hallucinations. Hallucination recognition and mitigation experiments with HalluCode and HumanEval show existing LLMs face great challenges in recognizing hallucinations, particularly in identifying their types, and are hardly able to mitigate hallucinations. We believe our findings will shed light on future research about hallucination evaluation, detection, and mitigation, ultimately paving the way for building more effective and reliable code LLMs in the future.

Yujia Chen, Yang Ye, Xiao Chu et al.

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%.

Yanli Wang, Yanlin Wang, Suiquan Wang et al.

Repository-level code translation refers to translating an entire code repository from one programming language to another while preserving the functionality of the source repository. Many benchmarks have been proposed to evaluate the performance of such code translators. However, previous benchmarks mostly provide fine-grained samples, focusing at either code snippet, function, or file-level code translation. Such benchmarks do not accurately reflect real-world demands, where entire repositories often need to be translated, involving longer code length and more complex functionalities. To address this gap, we propose a new benchmark, named RepoTransBench, which is a real-world repository-level code translation benchmark with an automatically executable test suite. We conduct experiments on RepoTransBench to evaluate the translation performance of 11 advanced LLMs. We find that the Success@1 score (test success in one attempt) of the best-performing LLM is only 7.33%. To further explore the potential of LLMs for repository-level code translation, we provide LLMs with error-related feedback to perform iterative debugging and observe an average 7.09% improvement on Success@1. However, even with this improvement, the Success@1 score of the best-performing LLM is only 21%, which may not meet the need for reliable automatic repository-level code translation. Finally, we conduct a detailed error analysis and highlight current LLMs' deficiencies in repository-level code translation, which could provide a reference for further improvements.

Yingli Zhou, Yaodong Su, Youran Sun et al.

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.

Shu Wang, Yixiang Fang, Yingli Zhou et al.

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.

Yanlin Wang, Kefeng Duan, Dewu Zheng et al.

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.

Yang Ye, Jingyuan Tan, Tianyue Jiang et al.

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.

Yanlin Wang, Tianyue Jiang, Mingwei Liu et al.

Large language models (LLMs) have brought a paradigm shift to the field of code generation, offering the potential to enhance the software development process. However, previous research mainly focuses on the accuracy of code generation, while coding style differences between LLMs and human developers remain under-explored. In this paper, we empirically analyze the differences in coding style between the code generated by mainstream Code LLMs and the code written by human developers, and summarize coding style inconsistency taxonomy. Specifically, we first summarize the types of coding style inconsistencies by manually analyzing a large number of generation results. We then compare the code generated by Code LLMs with the code written by human programmers in terms of readability, conciseness, and robustness. The results reveal that LLMs and developers have different coding styles. Additionally, we study the possible causes of these inconsistencies and provide some solutions to alleviate the problem.

Dong Chen, Shaoxin Lin, Muhan Zeng et al.

GitHub issue resolving recently has attracted significant attention from academia and industry. SWE-bench is proposed to measure the performance in resolving issues. In this paper, we propose CodeR, which adopts a multi-agent framework and pre-defined task graphs to Repair & Resolve reported bugs and add new features within code Repository. On SWE-bench lite, CodeR is able to solve 28.33% of issues, when submitting only once for each issue. We examine the performance impact of each design of CodeR and offer insights to advance this research direction.