activity
20212026
most citedNatural Attack for Pre-trained Models of Code

163 citations · 274 across the 45 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Second Thought: Reasoning in Parallel as LLM Agents Act and Observe

Zhensu Sun, Chengran Yang, Yunbo Lyu +2

LLM agents in the ReAct paradigm alternate between reasoning, acting, and observing, but deliberate reasoning is confined to the Thought phase: while the agent serializes an action…