most citedInjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

6 citations · 6 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Hidden States as Early Signals: Step-level Trace Evaluation and Pruning for Efficient Test-Time Scaling

Zhixiang Liang, Beichen Huang, Zheng Wang +1

Large Language Models (LLMs) can enhance reasoning capabilities through test-time scaling by generating multiple traces. However, the combination of lengthy reasoning traces with m…