Look Before You Leap: Autonomous Exploration for LLM Agents
Large language model based agents often fail in unfamiliar environments due to premature exploitation: a tendency to act on prior knowledge before acquiring sufficient environment-specific information. We identify autonomous exploration as a critical yet underexplored capability for building adaptive agents. To formalize and quantify this capability, we introduce Exploration Checkpoint Coverage, a verifiable metric that measures how broadly an agent discovers key states, objects, and affordances. Our systematic evaluation reveals that agents trained with standard task-oriented reinforcement learning consistently exhibit narrow and repetitive behaviors that impede downstream performance. To address this limitation, we develop a training strategy that interleaves task-execution rollouts and exploration rollouts, with each type of rollout optimized by its corresponding verifiable reward. Building on this training strategy, we propose the Explore-then-Act paradigm, which decouples information-gathering from task execution: agents first utilize an interaction budget to acquire grounded environmental knowledge, then leverage it for task resolution. Our results demonstrate that learning to systematically explore is imperative for building generalizable and real-world-ready agents.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
Look-ahead before you leap: end-to-end active recognition by forecasting the effect of motion
Visual recognition systems mounted on autonomous moving agents face the challenge of unconstrained data, but simultaneously have the opportunity to improve their performance by moving to acquire new views of test data. I…
Accelerate Langevin Sampling with Birth-Death Process and Exploration Component
Sampling a probability distribution with known likelihood is a fundamental task in computational science and engineering. Aiming at multimodality, we propose a new sampling method that takes advantage of both birth-death…
Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding
An LBYL (`Look Before You Leap') Network is proposed for end-to-end trainable one-stage visual grounding. The idea behind LBYL-Net is intuitive and straightforward: we follow a language's description to localize the targ…
DescriptiveObjectVisual GroundingA Survey of Data Agents: Emerging Paradigm or Overstated Hype?
The rapid advancement of large language models (LLMs) has spurred the emergence of data agents, autonomous systems designed to orchestrate Data + AI ecosystems for tackling complex data-related tasks. However, the term "…
Look Before You Leap: Improving Text-based Person Retrieval by Learning A Consistent Cross-modal Common Manifold
The core problem of text-based person retrieval is how to bridge the heterogeneous gap between multi-modal data. Many previous approaches contrive to learning a latent common manifold mapping paradigm following a \textbf…
Person RetrievalRetrievalText based Person RetrievalText-based Person Retrieval