โ† Back

MagicGUI-RMS: A Multi-Agent Reward Model System for Self-Evolving GUI Agents via Automated Feedback Reflux

Agent Tooling arxiv arXiv:2601.13060 PDF โ†—
rewardguirmsautomatedevolvingselffeedbackrefluxmagicgui
Introduces a multi-agent reward model system for GUI agents that combines domain-specific and general-purpose reward models with automated data reflux for self-evolving agent training.
5~10๋ถ„. ์ œ๋ชฉโ†’์ดˆ๋กโ†’์ธํŠธ๋กœโ†’์„น์…˜ํ—ค๋”โ†’๊ทธ๋ฆผโ†’๊ฒฐ๋ก ๋งŒ.
ํŒ๋‹จ: ์–ด๋–ค ๋ฌธ์ œ๋ฅผ ํ’€๊ณ  / ํ•ต์‹ฌ ์•„์ด๋””์–ด / ๋‚ด ์ž‘์—…๊ณผ ๊ด€๋ จ ์žˆ๋‚˜?
~1์‹œ๊ฐ„. ๊ทธ๋ฆผยทํ‘œ๋ฅผ ๊ผผ๊ผผํžˆ. ์ฆ๋ช…ยท์ˆ˜์‹ ๋””ํ…Œ์ผ์€ ๊ฑด๋„ˆ๋œ€.
์‚ฐ์ถœ๋ฌผ: "์ด๋“ค์ด ๋ญ˜ ํ–ˆ๊ณ  ์™œ ๊ทธ๊ฒŒ ํ†ตํ•˜๋Š”๊ฐ€" ํ•œ ๋ฌธ๋‹จ.
์žฌํ˜„ํ•˜๋“ฏ ์ฝ๊ธฐ. ๊ฐ€์ •์„ ์˜์‹ฌ. ์ง์ ‘ ์ธ์šฉ/๋ฐ˜๋ฐ•ํ•  ๋…ผ๋ฌธ๋งŒ.
๋ Œ์ฆˆ: "๋‚ด ํ”Œ๋ฆฟ์—์„œ ์ธก์ •ํ•˜๋ฉด ์ €์ž๊ฐ€ ๋ชป ํ•œ ๋ฌด์—‡์„ ๋ณด์—ฌ์ค„ ์ˆ˜ ์žˆ๋‚˜?"

Related Papers (10)

From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents
Agent Tooling unread sim 0.31
EvoConfig: Self-Evolving Multi-Agent Systems for Efficient Autonomous Environment Configuration
Agent Tooling unread sim 0.27
Towards AGI A Pragmatic Approach Towards Self Evolving Agent
Agent Tooling unread sim 0.24
The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordination
Multi-Agent unread sim 0.20
ToolTok: Tool Tokenization for Efficient and Generalizable GUI Agents
Agent Tooling unread sim 0.19
GUITester: Enabling GUI Agents for Exploratory Defect Discovery
Eval & Observability unread sim 0.18
RuleSmith: Multi-Agent LLMs for Automated Game Balancing
Multi-Agent unread sim 0.18
AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering
Agent Tooling unread sim 0.17
Learning with Challenges: Adaptive Difficulty-Aware Data Generation for Mobile GUI Agent Training
Agent Tooling unread sim 0.17
No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning
Agent Tooling unread sim 0.14
View in Knowledge Graph โ†’