Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents

• URL: http://arxiv.org/abs/2608.14339v1
• Date: Fri, 14 Aug 2026 14:24:50 GMT
• Title: Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents
• Abstract summary: ours is a novel method designed to instill and refine proactive exploration.<n>ours consists of two components: (1) Exploratory Data Construction, which synthesizes exploration-rich trajectories to mitigate the hindsight bias of standard demonstrations; and (2) RL Optimization with Contrastive Signal Guidance, which leverages contrastive trajectory pairs to distinguish productive exploration from redundant wandering.
• Score: 108.55958466397932
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study proactive exploration in LLM agents, i.e., the ability to explore an environment to acquire information that improves future decision-making. In this regard, we first identify two fundamental bottlenecks that hinder this capability and then propose \ours, a novel method designed to instill and refine proactive exploration. Specifically, \ours\ consists of two components: (1) Exploratory Data Construction, which synthesizes exploration-rich trajectories to mitigate the hindsight bias of standard demonstrations; and (2) RL Optimization with Contrastive Signal Guidance, which leverages contrastive trajectory pairs to distinguish productive exploration from redundant wandering. Extensive experiments demonstrate the effectiveness of \ours\ and provide insights into the characteristics of proactive exploration. Our code is available at: https://github.com/GuanZhizhao/SAFARI.

Related papers

• Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigation [49.96273402030084]
  We introduce Phi-Nav, a unified on-policy framework that leverages hindsight reasoning to align instructions with the agent's actual exploratory journey.<n>Phi-Nav bridges the critical semantic supervision gap inherent in on-policy methods, transforming semantically unlabeled movement into dense training signals.
  arXiv  Detail & Related papers  (2026-07-02T06:11:07Z)
• DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off [87.58233482504308]
  Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed significant advances in the reasoning capabilities of Large Language Models (LLMs)<n>This paper fully analyze the exploration and exploitation dilemma of extremely hard and easy samples during the training and propose a new fine-grained trade-off mechanism.
  arXiv  Detail & Related papers  (2026-04-15T14:12:10Z)
• Language-based Trial and Error Falls Behind in the Era of Experience [50.503828360874536]
  Large Language Models (LLMs) excel in language-based agentic tasks, but their applicability to unseen, nonlinguistic environments remains limited.<n>In this work, we demonstrate the primary bottleneck is the prohibitive cost of exploration.<n>We propose SCOUT, a novel framework that decouples exploration from semantic exploitation.
  arXiv  Detail & Related papers  (2026-01-29T14:08:41Z)
• Beyond the Exploration-Exploitation Trade-off: A Hidden State Approach for LLM Reasoning in RLVR [15.147456927849932]
  A prevailing view in Reinforcement Learning for Verifiable Rewards (RLVR) interprets recent progress through the lens of an exploration-exploitation trade-off.<n>We re-examine this perspective, proposing that this perceived trade-off may not be a fundamental constraint but rather an artifact of the measurement level.<n>We propose Velocity-Exploiting Rank-Learning (VERL), the first to operationalize the principle of synergistic exploration-exploitation enhancement.
  arXiv  Detail & Related papers  (2025-09-28T11:14:58Z)
• Deterministic Exploration via Stationary Bellman Error Maximization [6.474106100512158]
  Exploration is a crucial and distinctive aspect of reinforcement learning (RL) In this paper, we introduce three modifications to stabilize the latter and arrive at a deterministic exploration policy. Our experimental results show that our approach can outperform $varepsilon$-greedy in dense and sparse reward settings.
  arXiv  Detail & Related papers  (2024-10-31T11:46:48Z)
• Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents [49.85633804913796]
  We present an exploration-based trajectory optimization approach, referred to as ETO. This learning method is designed to enhance the performance of open LLM agents. Our experiments on three complex tasks demonstrate that ETO consistently surpasses baseline performance by a large margin.
  arXiv  Detail & Related papers  (2024-03-04T21:50:29Z)
• Curiosity & Entropy Driven Unsupervised RL in Multiple Environments [0.0]
  We propose and experiment with five new modifications to the original work. In high-dimensional environments, curiosity-driven exploration enhances learning by encouraging the agent to seek diverse experiences and explore the unknown more. However, its benefits are limited in low-dimensional and simpler environments where exploration possibilities are constrained and there is little that is truly unknown to the agent.
  arXiv  Detail & Related papers  (2024-01-08T19:25:40Z)
• Exploration in Deep Reinforcement Learning: A Comprehensive Survey [24.252352133705735]
  Deep Reinforcement Learning (DRL) and Deep Multi-agent Reinforcement Learning (MARL) have achieved significant success across a wide range of domains, such as game AI, autonomous vehicles, robotics and finance. DRL and deep MARL agents are widely known to be sample-inefficient and millions of interactions are usually needed even for relatively simple game settings. This paper provides a comprehensive survey on existing exploration methods in DRL and deep MARL.
  arXiv  Detail & Related papers  (2021-09-14T13:16:33Z)
• Deep Reinforcement Learning for Adaptive Exploration of Unknown Environments [6.90777229452271]
  We develop an adaptive exploration approach to trade off between exploration and exploitation in one single step for UAVs. The proposed approach uses a map segmentation technique to decompose the environment map into smaller, tractable maps. The results demonstrate that our proposed approach is capable of navigating through randomly generated environments and covering more AoI in less time steps compared to the baselines.
  arXiv  Detail & Related papers  (2021-05-04T16:29:44Z)
• Active Visual Information Gathering for Vision-Language Navigation [115.40768457718325]
  Vision-language navigation (VLN) is the task of entailing an agent to carry out navigational instructions inside photo-realistic environments. One of the key challenges in VLN is how to conduct a robust navigation by mitigating the uncertainty caused by ambiguous instructions and insufficient observation of the environment. This work draws inspiration from human navigation behavior and endows an agent with an active information gathering ability for a more intelligent VLN policy.
  arXiv  Detail & Related papers  (2020-07-15T23:54:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.