10 papers
MemTrace: Probing What Final Accuracy Misses in Long-Term Memory
Xianxuan Long, Zhikai Chen, Shenglai Zeng +3
LLM agents increasingly maintain long-term memory of user facts across sessions. Yet such memory is usually evaluated by aggregating accuracy over question rows or episodes. Becaus…
Magnifying What Matters: Attention-Guided Adaptive Rendering for Visual Text Comprehension
Shenglai Zeng, Qirui Wang, Kai Guo +3
Visual Text Comprehension (VTC) renders text into images for a vision-language model (VLM) to read, sidestepping LLM context-window limits and powering applications from long-page…
Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline
Zhikai Chen, Jialiang Gu, Junyu Yin +6
LLM agents accumulate histories that outgrow their context windows, motivating a growing literature on memory systems. Yet most existing designs are tuned to a single scenario (mul…
Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation
Shouren Wang, Wang Yang, Chuang Ma +7
Hybrid-thinking language models expose explicit /think and /no_think modes, but current designs do not separate them cleanly. Even in /no_think mode, models often emit long and sel…
How Uncertain Is the Grade? A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment
Hang Li, Kaiqi Yang, Xianxuan Long +9
The rapid rise of large language models (LLMs) is reshaping the landscape of automatic assessment in education. While these systems demonstrate substantial advantages in adaptabili…
When Truthful Representations Flip Under Deceptive Instructions?
Xianxuan Long, Yao Fu, Runchao Li +4
Large language models (LLMs) tend to follow maliciously crafted instructions to generate deceptive responses, posing safety challenges. How deceptive instructions alter the interna…