works on

From the 2 of 9 linked papers with an AI index.

collaborators

9 papers

cs.AI2026

Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

Mengru Wang, Junfeng Fang, Shuofei Qiao +16

AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their capabilities and the risks they may pose remain poorly understood. As AI deve…

cs.CL2026

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

Xinle Deng, Ruobin Zhong, Hujin Peng +15

The paper introduces MemTrace, a framework that converts large language model memory pipelines into executable graphs to trace and attribute errors, and provides a benchmark (MemTr…

cs.CL2026

LightMem-Ego: Your AI Memory for Everyday Life

Yijun Chen, Boyi Xiao, Yixian Zhao +10

The paper introduces LightMem-Ego, a lightweight on‑device system that continuously records egocentric video and audio, organizes them into hierarchical short‑ and long‑term memori…

cs.CL2026

TokenPilot: Cache-Efficient Context Management for LLM Agents

Buqiang Xu, Zirui Xue, Dianmou Chen +12

As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize…

cs.CL2026

Rethinking Memory as Continuously Evolving Connectivity

Jizhan Fang, Buqiang Xu, Zhixian Wang +12

Existing memory-augmented LLM agents often treat memory as a static repository with pre-defined representations and fixed retrieval pipelines, which is brittle in dynamic agentic e…

cs.CL2026

Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language

Yi Zhong, Buqiang Xu, Yijun Wang +4

At present, executable visual workflows have emerged as a mainstream paradigm in real-world industrial deployments, offering strong reliability and controllability. However, in cur…