paper-with-me

홈 › Papers

Toward Self-Evolution-Ready Workflow Harnesses: A Reversible Migration Path and Convertibility Taxonomy for Expert LLM Pipelines

2026-06-15 · Yimo Lin, Zhen Zhang, Yibin Li arxiv

While expert-validated "LLM + script" workflows deliver significant value, they remain static: they encode hard-won domain knowledge yet fail to adapt execution based on feedback. Existing agent research predominantly targets greenfield agents and synthetic benchmarks, leaving the migration of active legacy workflows unresolved. To bridge this gap, we present a reversible, Strangler-Fig migration path that refactors legacy workflows into composable, typed, and auditable stages. Central to this framework is a three-tier convertibility taxonomy (A/B/C), implemented as a routing stage within the system harness, which diagnoses a workflow's readiness and routes it accordingly.

📄 PDF Abstract BibTeX arXiv:2606.24598

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DarwinX: Evolving Agent Harnesses Through Natural Selection

2026-07-31 · Yifan Zhang, Yutong Dai, Juntao Tan, Luyu Yang 외 hf

An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow. Self-improvement loops already edit harnesses, yet single-lineage search is path-dependent and loc…

TTHE: Test-Time Harness Evolution

2026-07-09 · Jun Nie, Yonggang Zhang, Jun Song, Qianshu Cai 외 arxiv

The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies intermediate results, and recovers from failur…

Test-time Adaptation

COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows

2026-07-02 · Zongxia Li, Dawei Liu, Fuxiao Liu, Yuhang Zhou 외 arxiv

Agents are increasingly used to construct workflows and assist humans in completing recurring tasks more efficiently. As these workflows become repeated and domain-specific, agent memory and reusable skills become increa…

Image Generation

JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

2026-08-26 · Guibin Zhang, Leo Lu, Fangzhou Xie, Kang Zhu 외 arxiv

Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/skill orchestration, can dominate the contribution of the underlying …

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

2026-05-28 · Minhua Lin, Juncheng Wu, Zijun Wang, Zhan Shi 외 arxiv

LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task execution without changing model parameters. Harness self-evolution…

Instruction Following