From the 3 of 17 linked papers with an AI index.
17 papers
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…
Why Are GUI Agents Correct but Late? Decode on the Decision-Time Critical Path, Tested with Pre-Compiled Policy Trees
Zihan Dong, Rui Qian, Qishi Zhan +3
The paper introduces Adaptive Anticipatory Policy Trees (AAPT), a method that pre‑computes conditional action trees during idle screen time so GUI agents can react instantly to eve…
How Benchmarks Mis-Score Computer-Use Agents
Zihan Dong, Zhiyuan Ma, Zekun Wang +5
The paper examines how current benchmarks for computer-use agents often give inaccurate scores due to issues in task design, trajectory observation, scoring, and reporting, and pro…
Seeing What Is Actually There: PriVE-Bench and PriVE-Tools for Counterfactual Evaluation of Agentic Visual Evidence in VLMs
Jingyu Sun, Jiachen Tu, Yuyang Xue +8
Vision-language models (VLMs) often answer visual questions using learned language and category priors rather than grounding their predictions in the image itself. Counterfactual i…
Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Stateful Personal Agents
Xutao Mao, Liangjie Zhao, Leyao Wang +6
The paper defines persistent sycophancy, where personal agents store user‑provided claims in long‑term memory and later repeat them, and introduces the Personal Agent Sycophancy Be…