457 citations · 552 across the 18 of their papers we have counts for
7 papers · 1 filter
"You're Right, Let Me Fix It": How LLM Agents Damage Correct Work When Falsely Accused
Xutao Mao, Rui Qian, Longxiang Wang +6
LLM agents increasingly keep working after a task succeeds as they resume after compaction or take over handoffs. Their finished work keeps receiving follow-up input that sometimes…
MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents
Zhisheng Chen, Bingfan Zeng, Bangde Cao +8
Long-horizon agents rely on memory to reuse experiences, yet existing memory systems often assume that evidence can be directly consumed through a fixed representation. This leads…
PMMC: Prospective Multimodal Memory Compilation for Long-Term LVLM Agents
Jingyu Sun, Yan Lin, Yuyang Xue +10
Long-term memory is essential for LVLM agents to maintain consistency and integrate information across extended multimodal interactions. Existing agent memory systems, however, oft…
How Benchmarks Mis-Score Computer-Use Agents
Zihan Dong, Zhiyuan Ma, Zekun Wang +5
Computer-use agents (CUA) are being deployed to browse the web and operate desktop software, yet their benchmark scores are still commonly produced by brittle scripted oracles. A s…
Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Self-Improving Personal Agents
Xutao Mao, Liangjie Zhao, Leyao Wang +6
Self-improving personal agents write profiles, memories, and reusable skills that carry over from one chat to the next. Prior works ask whether a model agrees with the user in its…
Rubric-Guided Process Reward for Stepwise Model Routing
Shenghao Ye, Yu Guo, Zhengheng Li +2
Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent methods formulate routing as a sequenti…
CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning
Siyuan Ma, Bo Gao, Zikai Xiao +6
Recent test-time reasoning methods improve performance by generating more candidate chains or searching over larger reasoning trees, but they typically lack explicit control over w…