GRASP is a multi-stage planning framework that improves the reliability of large language models on complex tasks. It separates planning into three specialized modules—GenPlan for global macro-guidelines, RevPlan for exploring localized strategies, and VerPlan for multi-criteria evaluation—allowing context isolation and strict macro-regularization. Experiments show GRASP outperforms direct LLM planners by significant margins on datasets such as Natural Plan Calendar Scheduling, ZebraLogic, and SciBench Math, and it mitigates performance collapse in multi-task and dual-task settings.
By Arunabh Srivastava (Amir), Mohammad A. (Amir), Khojastepour, Srimat Chakradhar, Sennur Ulukus
arXiv:2508.01300v2 Announce Type: replace
Abstract: AI planning provides agents the ability to act autonomously towards achieving a goal in a given environment. Recent advances in Large Language Mode...
By Ma'ayan Armony, Albert Mero\~no-Pe\~nuela, Gerard Canal
GRASP is a multi-stage planning framework that separates planning into specialized modules: GenPlan for global macro-guidelines, RevPlan for exploring localized strategies, and VerPlan for multi-criteria evaluation. This strategy-aware approach yields state‑of‑the‑art accuracy on diverse datasets, outperforming direct LLM planners by up to 30.8% on ZebraLogic and reducing multi‑task degradation. GRASP’s context isolation and macro‑regularization also give it a 14.5% edge over frontier reasoning models like GPT‑5‑mini.
arXiv:2608. 16287v1 Announce Type: new Abstract: Joint-embedding predictive world models plan by scoring predicted terminal embeddings against a goal embedding using a cost defined on the representation itself.
By Jiaming Hu, Yan Zheng, Tian Wang
arXiv:2606. 27806v1 Announce Type: new Abstract: World models for language agents come in two useful forms.
By Xinyuan Song, Zekun Cai
LLM‑BabyBench transforms the BabyAI gridworld into a fully observable, purely textual setting that isolates planning as the sole source of failure. By serialising the entire grid, providing formal instructions, and validating actions deterministically, the benchmark introduces the PPD suite—Predict, Plan, and Decompose tasks—each scored with metrics that separate mission understanding from sequencing. Across a range of large language models, simulation accuracy is high while planning success drops sharply beyond a model‑specific horizon, revealing that plan length—not grid size—drives failure and that models often commit to a single corridor‑shaped route without backtracking.
By Idriss Malek, Omar Choukrani, Daniil Orel, Anh Duy Le Dinh, Zhuohan Xie, Zangir Iklassov, Martin Tak\'a\v{c}, Salem Lahlou
arXiv:2607. 11197v1 Announce Type: new Abstract: When LLMs exhibit uneven performance across planning tasks, these gaps are often attributed to task difficulty.
By Sukai Huang, Chenyuan Zhang, Fucai Ke, Zhixi Cai, Naim Rastgoo, Gholamreza Haffari, Hamid Rezatofighi
arXiv:2606. 03685v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) improves end-to-end classical planning in large language models (LLMs), but do these models also learn to represent and reason about the planning problems they are solving?
By Patrick Emami, Nan Qiang, Peter Graf
arXiv:2607. 14109v1 Announce Type: cross Abstract: Probing the capabilities of Large Language Models (LLMs) and building robust solutions for Multiple-Choice Question Answering (MCQA) remain central challenges in natural language understanding.
By Inder Preet, Shuxin Lin, Dhaval Patel
MemPlan is a memory‑conditioned PDDL planning framework designed for partially observable interactive text environments. It keeps the PDDL domain fixed and reconstructs the problem at each step using parsed observations, candidate hypotheses, and interaction memory, employing positive graph memory to assign relevance‑based action costs and negative memory to record refuted assumptions as exclusion constraints. Experiments on TextWorld, ALFWorld, and Robotouille demonstrate that MemPlan improves task completion and step efficiency over language‑only and PDDL‑aware baselines while significantly reducing online token cost compared with LLM‑planning baselines such as ReAct, and its fine‑tuned interface generalizes across task types without task‑specific fine‑tuning.
By Tengwei Song, Robert Hoehndorf
arXiv:2603. 29025v3 Announce Type: replace-cross Abstract: Large language models fail when a salient surface cue conflicts with an unstated feasibility constraint.
By Yubo Li, Lu Zhang, Tianchong Jiang, Ramayya Krishnan, Rema Padman
The paper investigates how different natural language plan representations affect the performance of large language model (LLM) web agents. Using the PlanAhead framework, the authors automatically classify WebArena tasks into three difficulty levels and evaluate four plan types—sequential subgoals, narrative, pseudocode, and checklist—on hard tasks across multiple multimodal LLM agents. They introduce a decomposition of Success Rate into Achievement Rate and Solved-Task Consistency to better understand stochastic variability, finding that both plan formulation and the LLM used to generate the plan significantly influence agent robustness and success.
By Alejandra Zambrano, Sara Vera Marjanovic, Imene Kerboua, Xing Han L\`u, Leila Kosseim