The paper introduces an expectation‑observation consistency verification (EOCV) mechanism for large language model (LLM) planning. EOCV allows batched executors to predict multiple actions in one model call while still grounding each step by comparing expected outcomes with actual observations. When consistency holds, execution continues; mismatches trigger early termination and replanning. Experiments on text‑based and multimodal benchmarks show that EOCV matches reactive executors in task performance while cutting weighted token usage by 29‑35% and works across different model backbones.
arXiv:2609.38108v1 Announce Type: new Abstract: Large language models (LLMs) enable agents to solve long-horizon tasks by generating a plan and then executing it in an environment. However, successfu...
arXiv:2609.36471v1 Announce Type: cross Abstract: World-Action Models (WAMs) improve robotic manipulation by conditioning action generation on predicted future observations, but future prediction add...
arXiv:2606. 14574v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as planners for autonomous agents in household environments.
The paper introduces the Agent-Editing World Model (AEWM), a new approach that models how reasoning and actions influence future task progress instead of simulating tool responses. AEWM includes an Action Judge that classifies decisions as Critical, Exploratory, or Noisy, and a State Revision mechanism that edits noisy reasoning–action continuations from the same observed history. The integrated system, EditAct, directly updates the underlying state during real execution, leading to significant performance gains across multiple benchmarks and agent backbones.
arXiv:2506. 09171v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly capable, but LLM agents still struggle to plan effectively in interactive, partially observable, long-horizon environments when search is unguided or recent history is insufficient.
arXiv:2607. 01942v1 Announce Type: new Abstract: LLM-based agents have shown strong potential for solving complex multi-step tasks, yet existing performance improvements often rely on either scaling to larger backbone models or task-specific fine-tuning.
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:2506.11578v5 Announce Type: replace Abstract: Recently, large language models (LLMs) have demonstrated strong performance, ranging from simple to complex tasks. However, while large models achi...
arXiv:2607. 17973v1 Announce Type: new Abstract: Latent world models have emerged as a powerful planning paradigm by learning action-conditioned predictive dynamics and using them as internal simulators to imagine and evaluate candidate action sequences.
arXiv:2606. 17924v1 Announce Type: cross Abstract: Current Vision-Language-Action (VLA) models face a trade-off between efficient action generation and explicit deliberation.
arXiv:2609.32754v2 Announce Type: replace Abstract: Large language model agents can often make reasonable local decisions on short tasks, yet their performance degrades when success requires long seq...
AtomTree is a hierarchical framework that enables state-aware task planning for embodied instruction following using large language models (LLMs). It incrementally constructs a tree of subgoals and actions, allowing the LLM to decide at each step whether to decompose further or output a grounded low-level action based on the current symbolic state. The system includes a lightweight memory module to summarize past outcomes and employs hierarchical backtracking replanning when a low-level action stalls, thereby preventing drift along incorrect trajectories. In zero-shot evaluation on the ALFRED benchmark, AtomTree outperforms prior LLM-based planners.