10 papers
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design
Anjie Liu, Ziqin Gong, Yan Song +6
Visual perception in modern Vision-Language Models (VLMs) is constrained by a perceptual bandwidth bottleneck: a broad field of view preserves global context but sacrifices the fin…
Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models
Kyuyoung Kim, Kevin Wang, Yunfei Xie +7
Training language models to produce both correct answers and sound reasoning remains an open challenge. Reinforcement learning with verifiable rewards typically optimizes only fina…
MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome
Fangda Ye, Yuxin Hu, Pengxiang Zhu +19
Recent progress in deep research systems has been impressive, but evaluation still lags behind real user needs. Existing benchmarks predominantly assess final reports using fixed r…
LexInstructEval: Lexical Instruction Following Evaluation for Large Language Models
Huimin Ren, Yan Liang, Baiqiao Su +4
The ability of Large Language Models (LLMs) to precisely follow complex and fine-grained lexical instructions is a cornerstone of their utility and controllability. However, evalua…
PyVision-RL: Forging Open Agentic Vision Models via RL
Shitian Zhao, Shaoheng Lin, Ming Li +4
Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefit…
SPAN: Benchmarking and Improving Cross-Calendar Temporal Reasoning of Large Language Models
Zhongjian Miao, Hao Fu, Chen Wei
We introduce SPAN, a cross-calendar temporal reasoning benchmark, which requires LLMs to perform intra-calendar temporal reasoning and inter-calendar temporal conversion. SPAN feat…