Cover Image

Same Signal, Different Semantics: A Cross-Framework Behavioral Analysis of Software Engineering Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Wei, Chen, Zhi, Gu, Jingxu, Li, Tianling, Liu, Shangqing, Jiang, Lingxiao
Format:	Preprint
Published:	2026
Subjects:	Software Engineering Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub Scenarios
by: Chen, Zhi, et al.
Published: (2025)

Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents
by: Chen, Zhi, et al.
Published: (2026)

Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios
by: Chen, Zhi, et al.
Published: (2024)

Unified Software Engineering Agent as AI Software Engineer
by: Applis, Leonhard, et al.
Published: (2025)

Promise and Peril of Collaborative Code Generation Models: Balancing Effectiveness and Memorization
by: Chen, Zhi, et al.
Published: (2024)

Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents
by: Zhao, Chenyu, et al.
Published: (2026)

ALMAS: an Autonomous LLM-based Multi-Agent Software Engineering Framework
by: Tawosi, Vali, et al.
Published: (2025)

Impact-driven Context Filtering For Cross-file Code Completion
by: Li, Yanzhou, et al.
Published: (2025)

Your Instructions Are Not Always Helpful: Assessing the Efficacy of Instruction Fine-tuning for Software Vulnerability Detection
by: Yusuf, Imam Nur Bani, et al.
Published: (2024)

Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities
by: Ma, Wei, et al.
Published: (2022)

AgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software Engineering
by: Kumar, Rajesh, et al.
Published: (2026)

Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute
by: Ma, Yingwei, et al.
Published: (2025)

SWE-Next: Scalable Real-World Software Engineering Tasks for Agents
by: Liang, Jiarong, et al.
Published: (2026)

Large Language Model-Based Agents for Software Engineering: A Survey
by: Liu, Junwei, et al.
Published: (2024)

Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling
by: Trae Research Team, et al.
Published: (2025)

Do Research Software Engineers and Software Engineering Researchers Speak the Same Language?
by: Kehrer, Timo, et al.
Published: (2025)

From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents
by: Ma, Murong, et al.
Published: (2026)

SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
by: Gong, Jingzhi, et al.
Published: (2026)

Accountable Agents in Software Engineering: An Analysis of Terms of Service and a Research Roadmap
by: Treude, Christoph
Published: (2026)

MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering
by: Guo, Chuanzhe, et al.
Published: (2026)

TOM-SWE: User Mental Modeling For Software Engineering Agents
by: Zhou, Xuhui, et al.
Published: (2025)

Do Code Semantics Help? A Comprehensive Study on Execution Trace-Based Information for Code Large Language Models
by: Wang, Jian, et al.
Published: (2025)

daVinci-Dev: Agent-native Mid-training for Software Engineering
by: Zeng, Ji, et al.
Published: (2026)

LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering
by: Qiu, Jielin, et al.
Published: (2025)

Towards Structured, State-Aware, and Execution-Grounded Reasoning for Software Engineering Agents
by: Tse-Hsun, et al.
Published: (2026)

Agents in Software Engineering: Survey, Landscape, and Vision
by: Wang, Yanlin, et al.
Published: (2024)

Transducer Tuning: Efficient Model Adaptation for Software Tasks Using Code Property Graphs
by: Yusuf, Imam Nur Bani, et al.
Published: (2024)

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
by: Han, Tingxu, et al.
Published: (2026)

FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair
by: Ma, Ruize, et al.
Published: (2026)

Same App, Different Behaviors: Uncovering Device-specific Behaviors in Android Apps
by: Dong, Zikan, et al.
Published: (2024)

Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents
by: de Macedo, Sanderson Oliveira, et al.
Published: (2026)

Prompt Stability in Code LLMs: Measuring Sensitivity across Emotion- and Personality-Driven Variations
by: Ma, Wei, et al.
Published: (2025)

HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
by: Phan, Huy Nhat, et al.
Published: (2024)

Structurally Aligned Subtask-Level Memory for Software Engineering Agents
by: Shen, Kangning, et al.
Published: (2026)

Lifecycle-Aware code generation: Leveraging Software Engineering Phases in LLMs
by: Xing, Xing, et al.
Published: (2025)

From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering
by: Dong, Tao, et al.
Published: (2025)

AgentGuard: A Multi-Agent Framework for Robust Package Confusion Detection via Hybrid Search and Metadata-Content Fusion
by: Li, Yu, et al.
Published: (2026)

Software Performance Engineering for Foundation Model-Powered Software
by: Zhang, Haoxiang, et al.
Published: (2024)

From Human Interfaces to Agent Interfaces: Rethinking Software Design in the Age of AI-Native Systems
by: Wang, Shaolin, et al.
Published: (2026)

OmniCode: A Benchmark for Evaluating Software Engineering Agents
by: Sonwane, Atharv, et al.
Published: (2026)