Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments

Qingyu Lu, Liang Ding, Siyi Cao, Xuebo Liu, Kanjian Zhang, Jinxia Zhang, Dacheng Tao


Abstract
Agents powered by large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments. However, such agents often suffer from inefficiencies in multi-turn interactions, frequently trapped in repetitive loops or issuing ineffective commands, leading to redundant computational overhead. Instead of relying solely on learning from trajectories, we take a first step toward exploring the early-exit behavior for LLM-based agents. We propose two complementary approaches, 1. an **intrinsic** method that injects exit instructions during generation, and 2. an **extrinsic** method that verifies task completion to determine when to halt an agent’s trial. To evaluate early-exit mechanisms, we introduce two metrics: one measures the reduction of **redundant steps** as a positive effect, and the other evaluates **progress degradation** as a negative effect. Experiments with 4 different LLMs across 5 embodied environments show significant efficiency improvements, with only minor drops in agent performance. We also validate a practical strategy where a stronger agent assists after an early-exit agent, achieving better performance with the same total steps. We will release our code to support further research.
Anthology ID:
2025.findings-emnlp.1304
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
24014–24027
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.1304/
DOI:
Bibkey:
Cite (ACL):
Qingyu Lu, Liang Ding, Siyi Cao, Xuebo Liu, Kanjian Zhang, Jinxia Zhang, and Dacheng Tao. 2025. Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 24014–24027, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments (Lu et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.1304.pdf
Checklist:
 2025.findings-emnlp.1304.checklist.pdf