6 papers
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
Bohan Lyu, Yucheng Yang, Siqiao Huang +25
Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities i…
Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning
Haozhe Wang, Qixin Xu, Changpeng Wang +4
Achieving robust perception-reasoning synergy is a central goal for advanced Vision-Language Models (VLMs). Recent advancements have pursued this goal via architectural designs or…
Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism
Haoxiang Zhang, Qixin Xu, Zhuofeng Li +4
Long-horizon search agents accumulate large amounts of retrieved content across many tool calls, making context-budget efficiency increasingly important. A minimal intervention is…
CogDoc: Towards Unified thinking in Documents
Qixin Xu, Haozhe Wang, Che Liu +2
Current document reasoning paradigms are constrained by a fundamental trade-off between scalability (processing long-context documents) and fidelity (capturing fine-grained, multim…
Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
Haozhe Wang, Qixin Xu, Che Liu +3
Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs), yet underlying mechanisms driving this success…
Reverse-Engineered Reasoning for Open-Ended Generation
Haozhe Wang, Haoran Que, Qixin Xu +9
While the ``deep reasoning'' paradigm has spurred significant advances in verifiable domains like mathematics, its application to open-ended, creative generation remains a critical…