Large Language Models (LLMs) have shown impressive performance on complex tasks through Chain-of-Thought (CoT) reasoning. However, conventional CoT relies on explicitly verbalized intermediate steps, which constrains its broader applicability, particularly in abstract reasoning tasks beyond language. To address this, there has been growing research interest in latent CoT reasoning, where the reasoning process is embedded entirely within latent spaces. By decoupling reasoning from explicit language generation, latent CoT offers the promise of richer cognitive representations and facilitates more flexible, faster inference. This paper aims to present a comprehensive overview of this emerging paradigm and establish a systematic taxonomy. We analyze recent advances in methods, categorizing them from token-wise horizontal approaches to layer-wise vertical strategies. We then provide in-depth discussions of these methods, highlighting their design principles, applications, and remaining challenges. We hope that our survey provides a structured foundation for advancing this promising direction in LLM reasoning.

Recent advancements in large language models (LLMs) have enabled agents to tackle complex embodied tasks through environmental interaction. However, these agents still make suboptimal decisions and perform ineffective actions, as they often overlook critical environmental feedback that differs from their internal beliefs. Through a formal probing analysis, we characterize this as belief inertia, a phenomenon where agents stubbornly adhere to prior beliefs despite explicit observations. To address this, we advocate active belief intervention, moving from passive understanding to active management. We introduce the Estimate-Verify-Update (EVU) mechanism, which empowers agents to predict expected outcomes, verify them against observations through explicit reasoning, and actively update prior beliefs based on the verification evidence. EVU is designed as a unified intervention mechanism that generates textual belief states explicitly, and can be integrated into both prompting-based and training-based agent reasoning methods. Extensive experiments across three embodied benchmarks demonstrate that EVU consistently yields substantial gains in task success rates. Further analyses validate that our approach effectively mitigates belief inertia, advancing the development of more robust embodied agents. Our code is available at https://github.com/WangHanLinHenry/EVU.

World models enable language agents to anticipate environment dynamics and evaluate candidate actions before execution, yet they are typically frozen after training, leaving them unable to adapt to the shifting on-policy distributions induced by evolving agents. Meanwhile, agent-improvement methods often depend on external rewards or verifiers that may be unavailable in realistic interactive environments. We introduce CoMap, a framework that co-evolves textual world models and agent policies through closed-loop interaction. At each decision step, the world model predicts future environment feedback for candidate actions, while the agent performs future-aware reflection by assessing the reliability of these predictions and refining its action accordingly. The resulting on-policy trajectories are then used to improve the world model through self-distillation, enabling it to continually adapt to the agent’s evolving interaction distribution. Across embodied task planning, web navigation, and tool-use benchmarks, CoMap consistently outperforms competitive baselines (e.g., a 16.75% relative improvement with Qwen3-4B). Further analyses show that this co-evolutionary process improves both world-model capability and long-horizon decision-making. Our code and data are available at: https://github.com/loyiv/CoMAP.

Recent advances in world models have shown promise for modeling future dynamics of environmental states, enabling agents to reason and act without accessing real environments. Current methods mainly perform single-step or fixed-horizon rollouts, leaving their potential for complex task planning under-exploited. We propose Imagine-then-Plan (ITP), a unified framework for agent learning via lookahead imagination, where an agent’s policy model interacts with the learned world model, yielding multi-step “imagined” trajectories. Since the imagination horizon may vary by tasks and stages, we introduce a novel adaptive lookahead mechanism by trading off the ultimate goal and task progress. The resulting imagined trajectories provide rich signals about future consequences, such as achieved progress and potential conflicts, which are fused with current observations, formulating a partially observable and imaginable Markov decision process to guide policy learning. We instantiate ITP with both training-free and reinforcement-trained variants. Extensive experiments across representative agent benchmarks demonstrate that ITP significantly outperforms competitive baselines. Further analyses validate that our adaptive lookahead largely enhances agents’ reasoning capability, providing valuable insights into addressing broader, complex tasks. Our code and data are publicly available at:https://github.com/loyiv/ITP.

Large language model (LLM)-based agents have shown promise in tackling complex tasks by interacting dynamically with the environment. Existing work primarily focuses on behavior cloning from expert demonstrations or preference learning through exploratory trajectory sampling. However, these methods often struggle to address long-horizon tasks, where suboptimal actions accumulate step by step, causing agents to deviate from correct task trajectories.To address this, we highlight the importance of timely calibration and the need to automatically construct calibration trajectories for training agents. We propose Step-Level Trajectory Calibration (STeCa), a novel framework for LLM agent learning. Specifically, STeCa identifies suboptimal actions through a step-level reward comparison during exploration. It constructs calibrated trajectories using LLM-driven reflection, enabling agents to learn from improved decision-making processes. We finally leverage these calibrated trajectories with successful trajectories for reinforced training.Extensive experiments demonstrate that STeCa significantly outperforms existing methods. Further analysis highlights that timely calibration enables agents to complete tasks with greater robustness. Our code and data are available at https://github.com/WangHanLinHenry/STeCa.

Zero-shot event detection is a challenging task. Recent research work proposed to use a pre-trained textual entailment (TE) model on this task. However, those methods treated the TE model as a frozen annotator. We treat the TE model as an annotator that can be enhanced. We propose to use TE models to annotate large-scale unlabeled text and use annotated data to finetune the TE model, yielding an improved TE model. Finally, the improved TE model is used for inference on the test set. To improve the efficiency, we propose to use keywords to filter out sentences with a low probability of expressing event(s). To improve the coverage of keywords, we expand limited number of seed keywords using WordNet, so that we can use the TE model to annotate unlabeled text efficiently. The experimental results show that our method can outperform other baselines by 15% on the ACE05 dataset.

Language models are exhibiting increasing capability in knowledge utilization and reasoning. However, when applied as agents in embodied environments, they often suffer from misalignment between their intrinsic knowledge and environmental knowledge, leading to infeasible actions. Traditional environment alignment methods, such as supervised learning on expert trajectories and reinforcement learning, encounter limitations in covering environmental knowledge and achieving efficient convergence, respectively. Inspired by human learning, we propose Exploration-based Error Correction Learning (E²CL), a novel framework that leverages exploration-induced errors and environmental feedback to enhance environment alignment for embodied agents. E²CL incorporates teacher-guided and teacher-free explorations to gather environmental feedback and correct erroneous actions. The agent learns to provide feedback and self-correct, thereby enhancing its adaptability to target environments. Extensive experiments in the VirtualHome environment demonstrate that E²CL-trained agents outperform those trained by baseline methods and exhibit superior self-correction capabilities.