Do Coding Agents Reuse Existing Code or Reinvent the Wheel?

arXiv:2609.35357 · cs.SE, cs.AI, cs.CL · Submitted 2026-09-28 · Read on arXiv

cs.SE, cs.AI, cs.CL

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/deepseek-ai/deepseek-harness

Terminology

• Redundancy — 19× in this paper · explained in 2 episodes
• Benchmark — 18× in this paper · explained in 2 episodes
• Core — 12× in this paper · explained in 2 episodes
• Benchmarking — 6× in this paper · explained in 3 episodes
• Verification — 4× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Agentic Coding — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• A Taxonomy of Inefficiencies in LLM-Generated Python Code
• Program Synthesis with Large Language Models
• Evaluating Large Language Models Trained on Code
• DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
• CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion
• LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
• SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades
• SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios
• LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation
• WebSailor: Navigating Super-human Reasoning for Web Agent
• MemOS: A Memory OS for AI System
• Code Copycat Conundrum: Demystifying Repetition in LLM-based Code Generation
• RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems
• CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
• SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
• MemGPT: Towards LLMs as Operating Systems
• EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative Interactions
• ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code
• Kimi K3: Open Frontier Intelligence

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