Retrieval-augmented generation (RAG) over visually rich documents must find both relevant content and the evidence that supports an answer. Screenshot retrieval preserves images and page structure, but written facts within screenshots also need to be searchable. Moreover, topical relevance alone does not identify which...
Zi-Niu Liu, Xiaoyang Chen, De-Zhi Ye et al.· 0 citations
Deep search agents solve knowledge-intensive tasks through long-horizon, multi-turn interactions, where assigning credit to individual search decisions is fundamentally difficult. Outcome-based reinforcement learning provides only a single terminal reward shared across an entire trajectory. Recent process-supervision m...
Si-Qi Chen, Zhengxi Lu, Yuchen Yan et al.· Proceedings of the 2026 Conf...· 0 citations
The introduced Programmatic Search Agent (PSA), which makes a local executable computation over candidates the unit of a search action, unifies a persistent candidate workspace, flexible primitive composition, and selective evidence presentation.
Jia-Ming Qian, Hui-Yan Yang, Man-Di Liu et al.· 0 citations
Deep search requires LLM agents to decompose complex queries, search for evidence, and synthesize grounded answers, yet existing ReAct-style agents suffer from two limitations: role coupling, where one policy must handle planning, evidence use, and synthesis; and context accumulation, where growing search histories int...
Xing-Yu Wu, Yuchen Yan, Zhengxi Lu et al.· 0 citations
This paper proposes UniRank, a Homogeneous Scaling framework that consolidates multiple ranking objectives into a single, unified generative model and introduces two paradigmatic innovations: Parallel Prediction via Task-Specific Anchors and Reinforcement Learning Optimization with Posterior CoT.
De-Zhi Ye, Junwei Hu, Xiaoyang Chen et al.· Proceedings of the 32nd ACM...· 0 citations
These findings suggest that, within the pointwise scoring paradigm, routing continuous relevance semantics through discrete text constrains ranking signal resolution reveals a bottleneck that is stable and difficult to overcome under current standard methods, rather than an easily resolvable training bias.
Xiaoyang Chen, Jie Liu, Hai-Jin Liang 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.
