6 papers
Evaluating Interactive Reasoning in Large Language Models: A Hierarchical Benchmark with Executable Games
Mingyuan Fan, Weiguang Han, Daixin Wang +3
We introduce a multi-turn interactive framework for reasoning evaluation that treats reasoning as active evidence acquisition and belief updating. Wherein, LLMs receive only the ta…
SRR-Judge: Step-Level Rating and Refinement for Enhancing Search-Integrated Reasoning in Search Agents
Chen Zhang, Kuicai Dong, Dexun Li +4
Recent deep search agents built on large reasoning models (LRMs) excel at complex question answering by iteratively planning, acting, and gathering evidence, a capability known as…
When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards
Mingyuan Fan, Weiguang Han, Daixin Wang +3
Reinforcement Learning with Verifiable Rewards (RLVR) is a central paradigm for turning large language models (LLMs) into reliable problem solvers, especially in logic-heavy domain…
Reinforcement Learning Foundations for Deep Research Systems: A Survey
Wenjun Li, Zhi Chen, Jingru Lin +8
Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarc…
Doc-Researcher: A Unified System for Multimodal Document Parsing and Deep Research
Kuicai Dong, Shurui Huang, Fangda Ye +9
Deep Research systems have revolutionized how LLMs solve complex questions through iterative reasoning and evidence gathering. However, current systems remain fundamentally constra…
From Long to Short: LLMs Excel at Trimming Own Reasoning Chains
Wei Han, Geng Zhan, Sicheng Yu +2
O1/R1 style large reasoning models (LRMs) signal a substantial leap forward over conventional instruction-following LLMs. By applying test-time scaling to generate extended reasoni…