Can Coding Agents Sustain Continual Evolution without Forgetting?
cs.SE, cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/THU-Agent/continual-harness-evolution
Terminology
Sources
- Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments
- HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer
- SWE-Bench-CL: Continual Learning for Coding Agents
- Overcoming catastrophic forgetting in neural networks
- Meta-Harness: End-to-End Optimization of Model Harnesses
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- Large Language Model-Based Agents for Software Engineering: A Survey
- Code as Agent Harness
- LifeMem: Enabling Lifelong Experience Reuse for LLM Agents
- AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents
- SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
- Self-Harness: Harnesses That Improve Themselves
- CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
- LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners
- Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters