Deep search enables language agents to solve complex information-seeking tasks through iterative web exploration. However, developing robust open-source agents remains challenging for three reasons. First, opaque trajectory-construction pipelines make training data difficult to audit and reproduce. Second, context comp...
Cong Pang, Jia-Qi Su, Cheng-Rui Wu et al.· 0 citations
Supervised fine-tuning of Model Context Protocol (MCP) agents is typically conducted on a static data distribution, which fails to adapt to the student's evolving capabilities and leaves newly exposed weaknesses insufficiently addressed. To address these challenges, we propose \method, an agent--data mutual evolution f...
Xuan-Ang Gao, Ke-Peng Lin, Xin-Yan Shi et al.· 0 citations
Algorithm-driven services, including search, recommendation, and advertising, rely on multi-stage model pipelines. While research prioritizes model optimization, post-deployment monitoring focuses on operational reliability. Yet operationally healthy systems may still produce poor-quality results, exposing a gap in exi...
Wen-Yi Xu, Ren-Zhe Zhou, Song-Yang Li et al.· 0 citations
ASPO introduces an Adaptive Query-Selection Mechanism (AQSM) that focuses training on queries at the policy's competence boundary: those it can solve but not yet reliably, and introduces substructure-level rewards that measure output-quality gains within each action's descendant subgraph.
Recursive self-improvement (RSI) aims to achieve compounding gains by having models improve themselves. While most existing RSI systems optimize external agent harnesses or prompts around a frozen base model, data-centric RSI directly updates the model's own parameters by training on agent-generated data. However, beca...
Zi-Qi Zhao, Fan-Qing Meng, Hao-Cheng Lu et al.· arXiv.org· 1 citation
Computer-using agents are increasingly capable of performing complex tasks in the digital world. To advance such agents, supervised learning on annotated interaction trajectories has become a common approach to improving their task-solving capabilities. However, high-quality interaction trajectories remain scarce for s...
Zhoumianze Liu, Zichen Ding, Bowen Yang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.