The Year in AI Papers
The year/Topics/Coding agents

Research collection

Coding agents

Software engineering with LLMs: SWE-style agents and harnesses, repository-level bug fixing, code generation models, and coding benchmarks.

Papers
30
Research labs
3
Official code
22

1–30 of 30 papers in this collection

01

Independent research

CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents

CodeNib is a multi-view data system that serves repository context to coding agents by building reusable lexical, dense, and structural views per repository commit, mapping outputs to repository-relative source ranges, and maintaining views across edits. It addresses three challenges: heterogeneous views (C1), incremental freshness (C2), and agent delivery…

Zhongming Yu, Hengjia Yu, Boqin Yuan, Shuting Zhao, et al.
Published
Jul 2026
Citations
0
Code
74 stars
Read summary Original
02

Independent research

SWE-Pruner Pro: The Coder LLM Already Knows What to Prune

SWE-Pruner Pro is a method for pruning long tool outputs in coding agents by reading line-level importance directly from the agent's own internal representations, eliminating the need for a separate scoring model or explicit goal-hint query. A lightweight head, trained with a per-sample balanced focal loss and a length-aware embedding, converts the frozen…

Yuhang Wang, Yuling Shi, Shaoqiu Zhang, Jialiang Liang, et al.
Published
Jul 2026
Citations
0
Code
16 stars
Read summary Original
03

Independent research

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

The paper introduces Harness Handbook, a behavior-centric representation for agent harnesses that links system behaviors to their distributed source implementations, addressing the challenge of behavior localization during harness evolution. It is constructed automatically via static analysis and LLM-assisted structuring, organizing knowledge into a…

Ruhan Wang, Yucheng Shi, Zongxia Li, Zhongzhi Li, et al.
Published
Jul 2026
Citations
1
Code
292 stars
Read summary Original
04

Independent research

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

This paper introduces function-aware fill-in-the-middle (FIM) mid-training to improve coding agent foundation models. The authors observe that a coding agent's action-observation-continuation loop is structurally similar to a function call site, and they exploit this by masking functions selected via program dependency graph analysis and a…

Yubo Wang, Jiarong Liang, Yuxuan Zhang, Xuye Liu, et al.
Published
Jul 2026
Citations
0
Code
18 stars
Read summary Original
05

Independent research

Dockerless: Environment-Free Program Verifier for Coding Agents

Dockerless is an environment-free agentic program verifier that evaluates code patches without executing them, using agentic repository exploration to gather evidence. It generates verification questions from the issue and reference patch, dispatches parallel sub-agents to collect evidence-backed answers, and produces a correctness score. Trained via…

Wenhao Zeng, Yuling Shi, Xiaodong Gu, Chao Hu, et al.
Published
Jun 2026
Citations
1
Code
Not linked
Read summary Original
06

Together AI

ParallelKernelBench: Benchmarking LLMs on Multi-GPU Kernel Generation

The paper introduces ParallelKernelBench (PKB), a benchmark for evaluating LLMs on multi-GPU CUDA kernel generation. PKB includes 87 problems spanning parallelism strategies (tensor, expert, data, sequence, context) and real workloads from production frameworks. Evaluations of frontier models (GPT-5.5, Opus-4.7, Gemini 3 Pro, GLM-5.2, DeepSeek V4 Pro) show…

Willy Chan, Nathan Paek, Simon Guo, Simran Arora, et al.
Published
Jun 2026
Citations
Not indexed
Code
47 stars
Read summary Original
07

Independent research

Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages

Multi-LCB is a benchmark extending LiveCodeBench (LCB) to twelve programming languages (C++, C#, Python, Java, Rust, Go, TypeScript, JavaScript, Ruby, PHP, Kotlin, Scala) to evaluate LLM code generation beyond Python. It converts LCB's Python tasks into a unified STDIN/STDOUT format, preserving contamination controls and evaluation protocol, and…

Maria Ivanova, Pavel Zadorozhny, Rodion Levichev, Ivan Petrov, et al.
Published
Jun 2026
Citations
1
Code
27 stars
Read summary Original
08

Independent research

GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?

GameCraft-Bench is a benchmark for evaluating coding agents on end-to-end game generation in the Godot engine. It formalizes the task as transforming natural-language specifications into complete, playable game projects, requiring three desiderata: Engine Grounding, Artifact Completeness, and Interactive Verification. The benchmark includes 140 tasks…

Tongxu Luo, Rongsheng Wang, Jiaxi Bi, Chenming Xu, et al.
Published
Jun 2026
Citations
1
Code
191 stars
Read summary Original
09

arXiv.org

OpenGame: Open Agentic Coding for Games

OpenGame is an open-source agentic framework for end-to-end web game creation from natural-language specifications. It introduces Game Skill, comprising a Template Skill that evolves a library of project skeletons and a Debug Skill that maintains a living protocol of verified fixes, to address cross-file inconsistencies and integration errors. The…

Yilei Jiang, Jinyuan Hu, Qianyin Xiao, Yaozhi Zheng, et al.
Published
Apr 2026
Citations
5
Code
2.8K stars
Read summary Original
10

arXiv.org

InCoder-32B-Thinking: Industrial Code World Model for Thinking

The paper introduces InCoder-32B-Thinking, a 32B-parameter code model trained to reason about industrial software development (chip design, GPU optimization, embedded systems, 3D modeling) by integrating an Error-driven Chain-of-Thought (ECoT) synthesis framework and an Industrial Code World Model (ICWM). ECoT generates reasoning traces by modeling…

Jian Yang, Wei Zhang, Jiajun Wu, Junhang Cheng, et al.
Published
Apr 2026
Citations
3
Code
Not linked
Read summary Original
11

arXiv.org

Embarrassingly Simple Self-Distillation Improves Code Generation

The paper introduces Simple Self-Distillation (SSD), a method that improves LLM code generation by sampling solutions from the model itself with specific temperature and truncation settings, then fine-tuning on those raw, unverified outputs via standard supervised fine-tuning. SSD requires no verifier, teacher model, or reinforcement learning. It improves…

Ruixiang Zhang, Richard He Bai, Huangjie Zheng, Navdeep Jaitly, et al.
Published
Apr 2026
Citations
28
Code
798 stars
Read summary Original
12

arXiv.org

QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation

QuanBench+ is a unified benchmark for evaluating LLMs on quantum code generation across Qiskit, PennyLane, and Cirq, holding task intent constant while varying the framework. It includes 42 tasks spanning quantum algorithms, gate decomposition, and state preparation, and uses executable functional tests with Pass@1, Pass@5, and KL-divergence-based…

Ali Slim, Haydar Hamieh, Jawad Kotaich, Yehya Ghosn, et al.
Published
Mar 2026
Citations
1
Code
6 stars
Read summary Original
13

arXiv.org

InCoder-32B: Code Foundation Model for Industrial Scenarios

InCoder-32B is a 32B-parameter code foundation model designed to unify code intelligence across general programming and industrial domains such as chip design, GPU kernel optimization, embedded systems, compiler optimization, and 3D modeling. It is trained from scratch using a three-stage Code-Flow pipeline: pre-training with curated industrial data,…

Jian Yang, Wei Zhang, Jiajun Wu, Junhang Cheng, et al.
Published
Mar 2026
Citations
6
Code
Not linked
Read summary Original
14

arXiv.org

BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?

BeyondSWE is a 500-instance benchmark from 246 real GitHub repositories that evaluates code agents beyond single-repository bug fixing, covering four settings: cross-repository issue resolution (CrossRepo), domain-specific issue resolution (DomainFix), dependency-driven migration (DepMigrate), and document-to-repository generation (Doc2Repo). These tasks…

Guoxin Chen, Fanzhe Meng, Jiale Zhao, Minghao Li, et al.
Published
Mar 2026
Citations
11
Code
47 stars
Read summary Original
15

Qwen

Qwen3-Coder-Next Technical Report

Qwen3-Coder-Next is an 80-billion-parameter open-weight language model with only 3 billion active parameters per forward pass, designed for coding agents. It is built on Qwen3-Next with hybrid attention and Mixture-of-Experts, and trained via a staged pipeline: continued pretraining on code and agent-centric data, supervised fine-tuning, and reinforcement…

Ruisheng Cao, Mouxiang Chen, Jiawei Chen, Zeyu Cui, et al.
Published
Feb 2026
Citations
54
Code
17K stars
Read summary Original
16

arXiv.org

SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale

SWE-rebench V2 introduces a language-agnostic automated pipeline for harvesting executable real-world software engineering (SWE) tasks at scale, addressing the scarcity of large-scale training data for reinforcement learning (RL). The pipeline mines pull request histories, synthesizes repository-specific installation and test procedures via an interactive…

Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov, Alexander Golubev
Published
Feb 2026
Citations
11
Code
76 stars
Read summary Original
17

Z.ai / GLM

GLM-5: from Vibe Coding to Agentic Engineering

GLM-5, developed by Zhipu AI and Tsinghua University, is a next-generation foundation model that shifts from vibe coding to agentic engineering. It builds on the ARC (agentic, reasoning, coding) capabilities of its predecessor, GLM-4.7, and introduces DeepSeek Sparse Attention (DSA) to reduce training and inference costs while maintaining long-context…

GLM-5-Team, :, Aohan Zeng, Xin Lv, et al.
Published
Feb 2026
Citations
295
Code
6.9K stars
Read summary Original
18

Qwen

SWE-Universe: Scale Real-World Verifiable Environments to Millions

SWE-Universe is a framework for automatically constructing real-world software engineering (SWE) verifiable environments from GitHub pull requests (PRs) at a million scale. It addresses challenges of low production yield, weak verifiers, and prohibitive cost using a building agent powered by a custom-trained MoE model (Qwen-Next-80B-A3B). The agent uses…

Mouxiang Chen, Lei Zhang, Yunlong Feng, Xuwu Wang, et al.
Published
Feb 2026
Citations
7
Code
Not linked
Read summary Original
19

Open MIND

Closing the Loop: Universal Repository Representation with RPG-Encoder

RPG-Encoder generalizes the Repository Planning Graph (RPG) into a unified, high-fidelity representation for repository reasoning, closing the loop between comprehension and generation. It addresses the disconnect caused by fragmented representations (API documentation lacks structure, dependency graphs lack semantics) by encoding raw code into a dual-view…

Jane Luo, Chengyu Yin, Xin Zhang, Qingtao Li, et al.
Published
Feb 2026
Citations
0
Code
588 stars
Read summary Original
20

arXiv.org

daVinci-Dev: Agent-native Mid-training for Software Engineering

The paper introduces daVinci-Dev, a training recipe for agentic software engineering that uses agent-native mid-training data to bridge the gap between static training corpora and dynamic, feedback-rich development environments. The authors construct two complementary trajectory types: contextually-native trajectories (68.6B tokens) derived from GitHub…

Ji Zeng, Dayuan Fu, Tiantian Mi, Yumin Zhuang, et al.
Published
Jan 2026
Citations
10
Code
73 stars
Read summary Original
21

arXiv.org

SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents

SWE-Pruner is a self-adaptive context pruning framework for coding agents, addressing the high API costs and latency from long interaction contexts. It uses a lightweight 0.6B neural skimmer, trained on 61K synthetic samples, to perform task-aware, line-level pruning based on a goal hint provided by the agent. Evaluated on multi-turn tasks (SWE-Bench…

Yuhang Wang, Yuling Shi, Mo Yang, Rongrui Zhang, et al.
Published
Jan 2026
Citations
26
Code
304 stars
Read summary Original
22

arXiv.org

Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model

Stable-DiffCoder is a diffusion-based language model for code that reuses the Seed-Coder architecture, data, and training pipeline but replaces autoregressive (AR) training with a block diffusion continual pretraining (CPT) stage. The authors introduce a tailored warmup and a block-wise clipped noise schedule to stabilize training and improve knowledge…

Chenghao Fan, Wen Heng, Bo Li, Sichen Liu, et al.
Published
Jan 2026
Citations
13
Code
84 stars
Read summary Original
23

arXiv.org

Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey

This paper presents a systematic survey of LLM-based issue resolution in software engineering, a task formalized by benchmarks like SWE-bench. The survey reviews 175 papers, organizing the field into a taxonomy covering data, methods, and analysis. Data is categorized into evaluation and training datasets, with construction via automated collection or…

Caihua Li, Lianghong Guo, Yanlin Wang, Daya Guo, et al.
Published
Jan 2026
Citations
7
Code
86 stars
Read summary Original
24

arXiv.org

Controlled Self-Evolution for Algorithmic Code Optimization

The paper introduces Controlled Self-Evolution (CSE), a framework to improve the exploration efficiency of self-evolution methods for algorithmic code optimization. CSE addresses three bottlenecks: initialization bias, uncontrolled stochastic evolution, and insufficient experience utilization. It comprises three components: Diversified Planning…

Tu Hu, Ronghao Chen, Shuo Zhang, Jianghao Yin, et al.
Published
Jan 2026
Citations
11
Code
131 stars
Read summary Original
25

arXiv.org

MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences

MemGovern is a framework that transforms raw GitHub issue-tracking data into structured, agent-friendly experiential memory to enhance autonomous software engineering (SWE) agents. It addresses the 'closed-world' limitation of agents that ignore historical human debugging experience. MemGovern uses experience governance to filter, standardize, and…

Qihao Wang, Ziming Cheng, Shuo Zhang, Fan Liu, et al.
Published
Jan 2026
Citations
8
Code
Not linked
Read summary Original
26

arXiv.org

From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence

This survey comprehensively examines the lifecycle of code-focused large language models (LLMs), from data curation and pre-training to post-training, alignment, and deployment as autonomous agents. It analyzes both general-purpose LLMs (e.g., GPT-4, Claude, LLaMA) and code-specialized models (e.g., StarCoder, Code LLaMA, DeepSeek-Coder, QwenCoder),…

Jian Yang, Xianglong Liu, Weifeng Lv, Ken Deng, et al.
Published
Nov 2025
Citations
12
Code
Not linked
Read summary Original
27

arXiv.org

JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence

The paper introduces JANUSCODER, a suite of foundational models for multimodal code intelligence, establishing a unified visual-programmatic interface. It addresses the scarcity of high-quality multimodal code data by developing a data synthesis toolkit that leverages synergies between data modalities. This toolkit enables the creation of JANUSCODE-800K,…

Qiushi Sun, Jingyang Gong, Yang Liu, Qiaosheng Chen, et al.
Published
Oct 2025
Citations
7
Code
78 stars
Read summary Original
28

arXiv.org

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

The paper introduces the Repository Planning Graph (RPG), a structured representation that unifies proposal-level and implementation-level planning for generating complete software repositories from high-level specifications. RPG encodes capabilities, file structures, data flows, and functions as nodes and edges, replacing ambiguous natural language plans.…

Jane Luo, Xin Zhang, Steven Liu, Jie Wu, et al.
Published
Sep 2025
Citations
12
Code
Not linked
Read summary Original
29

Annual Meeting of the Association for Computational Linguistics

A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code

The paper introduces A.S.E (AI Code Generation Security Evaluation), a repository-level benchmark for assessing the security of AI-generated code. It is built from 120 instances derived from 40 real-world GitHub repositories with documented CVEs, expanded via semantic and structural mutations. The benchmark covers four vulnerability types (SQL injection,…

Keke Lian, Bin Wang, Lei Zhang, Libo Chen, et al.
Published
Aug 2025
Citations
15
Code
647 stars
Read summary Original
30

arXiv.org

Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

The paper presents a two-phase training pipeline for software engineering (SWE) agents using reinforcement learning (RL). Starting from Qwen2.5-72B-Instruct, the authors first apply rejection fine-tuning (RFT) on successful trajectories from SWE-rebench tasks, improving Pass@1 on SWE-bench Verified from 11% to 20%. Then, they apply a synchronous RL…

Alexander Golubev, Maria Trofimova, Sergei Polezhaev, Ibragim Badertdinov, et al.
Published
Aug 2025
Citations
27
Code
Not linked
Read summary Original