arXiv Computation and Language November 4, 2026 By Qingfu Zhu, Huanyang Zheng, Ting Liu, Wanxiang Che

As Expected? Efficient LLM Planning via Expectation-Observation Consistency Verification

Read the original on arXiv Computation and Language →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Sep 30

Do LLM Agents Execute the Plans They Declare? From Planning-Mode Declaration to Pattern-Specific Execution

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...

By Subba Reddy Oota, Francisco Herrera, Jordi Cabot Sagrera, Marcos L\'opez de Prado, Shadab Khan

llms agents benchmarks

arXiv AI

Sep 30

Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks

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...

By Guoheng Sun, Chen Chen, Jin Wang, Ang Li, Teresa Lv

rag robotics efficiency

arXiv AI

Jun 15

SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model

arXiv:2606. 14574v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as planners for autonomous agents in household environments.

By Xiaoxin Lu, Ranran Haoran Zhang, Rui Zhang

llms agents benchmarks

arXiv AI

Sep 24

Agent-Editing World Model: Rethinking World Modeling for LLM Agents

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.

By Shuang Sun, Guoxin Chen, Fanzhe Meng, Jia Deng, Huatong Song, Jinhao Jiang, Wayne Xin Zhao, Hongteng Xu, Ji-Rong Wen

llms agents fine-tuning benchmarks

arXiv AI

Jun 10

Fact-Augmented Lookahead Planning for LLM Agents

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.

By Samuel Holt, Max Ruiz Luyten, Thomas Pouplin, Mihaela van der Schaar

llms agents

arXiv AI

Jul 3

Atomic Task Graph: A Unified Framework for Agentic Planning and Execution

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.

By Yue Zhang, Sihan Chen, Ziwen Huang, Hanyun Cui, Kangye Ji, Zhi Wang

llms agents fine-tuning benchmarks

One email a morning, machine-written

Related stories

Do LLM Agents Execute the Plans They Declare? From Planning-Mode Declaration to Pattern-Specific Execution

Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks

SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model

Agent-Editing World Model: Rethinking World Modeling for LLM Agents

Fact-Augmented Lookahead Planning for LLM Agents

Atomic Task Graph: A Unified Framework for Agentic Planning and Execution