arXiv:2608. 14339v1 Announce Type: new Abstract: We study proactive exploration in LLM agents, i.
arXiv:2607. 01754v1 Announce Type: new Abstract: On-policy exploration is a crucial component for training robust Vision-Language Navigation agents, as it exposes the policy to a broader state distribution.
On-policy exploration is a crucial component for training robust Vision-Language Navigation agents, as it exposes the policy to a broader state distribution. However, such exploration inevitably leads to trajectories that deviate from expert demonstrations, resulting in a semantic mismatch between the executed visual stream and the original language instruction.
arXiv:2607. 29419v1 Announce Type: cross Abstract: In reinforcement learning, exploration with sparse and delayed rewards presents a significant challenge due to the limited feedback available for guiding the learning process.
arXiv:2607. 08837v1 Announce Type: cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers.
arXiv:2410. 02511v2 Announce Type: replace Abstract: With expansive state-action spaces, efficient multi-agent exploration remains a longstanding challenge in reinforcement learning.
arXiv:2601. 21754v3 Announce Type: replace Abstract: While Large Language Models (LLMs) excel in language-based agentic tasks, their applicability to unseen, nonlinguistic environments (e.
arXiv:2606. 14879v1 Announce Type: cross Abstract: Mobile agents require efficient exploration strategies to map unseen environments and autonomously plan tasks.
arXiv:2606. 18388v1 Announce Type: cross Abstract: RL post-training strategies are dataset-dependent and reveal a recurring empirical pattern: capacity parameters accumulate monotonically across stages, while regularization parameters predominantly oscillate in response to shifting training dynamics.
arXiv:2606. 24064v1 Announce Type: new Abstract: Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather than how to reason.
arXiv:2606. 19656v1 Announce Type: cross Abstract: A natural recipe for intelligent robotic decision-making is initializing from pretrained generative control policies, which have summarized offline experience, and adapting them to self-collected online experience.
arXiv:2607. 12236v1 Announce Type: new Abstract: Speculative execution accelerates LLM agents by using a smaller, cheaper model to predict and pre-launch the next step while the environment is idle.
arXiv:2606. 12550v1 Announce Type: cross Abstract: Open-world mapless navigation from sparse language instructions requires resolving underspecified goals and inferring which environmental cues are relevant for reaching the goal.