paper-with-me

Papers

SePO: Self-Evolving Prompt Agent for System Prompt Optimization

2026-06-03 · Wangcheng Tao, Han Wu, Weng-Fai Wong arxiv

System prompt optimization improves agent behavior without modifying the underlying model, yielding human-readable, model-agnostic instructions. Existing methods build a prompt agent that refines task agents' system prompts, yet leave the prompt agent's own system prompt hand-engineered and fixed. We propose Self-Evolving Prompt Optimization (SePO), which treats the prompt agent's own system prompt as an optimization target alongside task agents' system prompts. SePO adopts a self-referential design. A single prompt agent improves both task agents' system prompts and its own under an open-ended evolutionary search that maintains an archive of candidate prompts as stepping stones. Training proceeds in two stages: pre-training evolves the prompt agent on a multi-task pool, and fine-tuning then applies it to a target task. Across five benchmarks spanning math (AIME'25), abstract reasoning (ARC-AGI-1), graduate-level science (GPQA), code generation (MBPP), and logic puzzles (Sudoku), SePO consistently outperforms Manual-CoT, TextGrad, and MetaSPO, improving the average accuracy by 4.49 points compared to Manual-CoT. The prompt optimization skill from pre-training also generalizes to tasks beyond the pre-training mixture, rather than memorizing per-task prompts.

📄 PDF Abstract BibTeX arXiv:2606.04465

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

SEPO: Evidence-Grounded Prompt Optimization via Structural Editing

2026-08-28 · Xiaoyu Ma, Haoyue Liu, Yiwen Li, Jionghao Zhu 외 arxiv

Existing API-only prompt optimisers are often described as interpretable, but in practice, this usually means only post-hoc inspectability: each iteration still rewrites the prompt as one opaque string, leaving a trace o…

Safe Equilibrium Policy Optimization for Strategic Agent Policies

2026-05-29 · Karthika Arumugam, Kiran Kumar Manku, Amit Dhanda arxiv

Language models fine-tuned with reinforcement learning typically optimize for task reward, ignoring multi-agent strategic structure. Because these agents condition on natural language game-state descriptions and emit act…

Reinforcement Learning

From Agentification to Self-Evolving Agentic AI for Wireless Networks: Concepts, Approaches, and Future Research Directions

2025-10-07 · Changyuan Zhao, Ruichen Zhang, Jiacheng Wang, Dusit Niyato 외 arxiv

Self-evolving agentic artificial intelligence (AI) offers a new paradigm for future wireless systems by enabling autonomous agents to continually adapt and improve without human intervention. Unlike static AI models, sel…

Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration

2025-09-12 · Xingchen Wan, Han Zhou, Ruoxi Sun, Hootan Nakhost 외 arxiv

Text-to-image (T2I) models, while offering immense creative potential, are highly reliant on human intervention, posing significant usability challenges that often necessitate manual, iterative prompt engineering over of…

Text-to-Image GenerationPrompt Engineering

Agents of Change: Self-Evolving LLM Agents for Strategic Planning

2025-06-05 · Nikolas Belle, Dakota Barnes, Alfonso Amayuelas, Ivan Bercovich 외

Recent advances in LLMs have enabled their use as autonomous agents across a range of tasks, yet they continue to struggle with formulating and adhering to coherent long-term strategies. In this paper, we investigate whe…