Harness Engineering for Software Engineering via Modular Executable Dev-Primitives
cs.SE, cs.AI, cs.CL, cs.MA
Submitted: 2026-10-06
Updated: 2026-10-06
Sources
- CodeR: Issue Resolving with Multi-Agent and Task Graphs
- NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents
- Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems
- Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives
- SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios
- CODESKILL: Learning Self-Evolving Skills for Coding Agents
- MarsCode Agent: AI-native Automated Bug Fixing
- From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents
- Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement
- Training Software Engineering Agents and Verifiers with SWE-Gym
- AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes
- Executable Code Actions Elicit Better LLM Agents
- CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Qwen3 Technical Report
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties