attention dynamics 1efficiency 1evaluation benchmark 1large language models 1multimodal large language models 1multi-turn dialogue 1role-playing agents 1token pruning 1training-free methods 1user simulation 1
From the 2 of 3 linked papers with an AI index.
3 papers
cs.CV2026
Capturing Token Tendencies for Training-Free Token Pruning in Multimodal Large Language Models
Jie Ma, Zhike Qiu, Jie Gao +4
The paper introduces Trend-aware Pruning, a training‑free method that models the temporal dynamics of attention to selectively keep visual tokens that become important in deeper la…
cs.CL2026
Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation
Yuhang Zhu, Mingxuan Du, Benfeng Xu +3
The paper presents PALATE, a benchmark that uses per‑user simulated agents to evaluate role‑playing language models through free‑form, multi‑turn conversations and personalized sat…
cs.AI2026
One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution
Jie Ma, Binfei Chu, Jie Gao +6
Autonomous research agents can now draft hypotheses, write code, run experiments, and produce papers, but they remain brittle when experiments fail. Under the prevailing paradigm,…