Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents
Xutao Mao, Liangjie Zhao, Xiang Zheng +1
LLM agents increasingly save experience from past tasks as reusable skills through skill evolution. When an agent completes an unsafe task, skill evolution can keep the unsafe proc…
cs.AI2026
What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis
Xutao Mao, Jinman Zhao, Gerald Penn +1
Agent memory failures are silent: an LLM-based agent can produce a fluent response even when it fails to extract, retain, or retrieve the information needed across sessions. The wr…
cs.AI2025
SteinerSQL: Graph-Guided Mathematical Reasoning for Text-to-SQL Generation
Xutao Mao, Tao Liu, Hongying Zan
Large Language Models (LLMs) struggle with complex Text-to-SQL queries that demand both sophisticated mathematical reasoning and intricate schema navigation. Existing methods often…