LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench

• URL: http://arxiv.org/abs/2409.13373v1
• Date: Fri, 20 Sep 2024 10:20:46 GMT
• Title: LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench
• Abstract summary: PlanBench is a benchmark for evaluating the planning abilities of large language models (LLMs) This paper takes a comprehensive look at how well current LLMs and new LRMs do on PlanBench.
• Score: 17.329365493094542
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The ability to plan a course of action that achieves a desired state of affairs has long been considered a core competence of intelligent agents and has been an integral part of AI research since its inception. With the advent of large language models (LLMs), there has been considerable interest in the question of whether or not they possess such planning abilities. PlanBench, an extensible benchmark we developed in 2022, soon after the release of GPT3, has remained an important tool for evaluating the planning abilities of LLMs. Despite the slew of new private and open source LLMs since GPT3, progress on this benchmark has been surprisingly slow. OpenAI claims that their recent o1 (Strawberry) model has been specifically constructed and trained to escape the normal limitations of autoregressive LLMs--making it a new kind of model: a Large Reasoning Model (LRM). Using this development as a catalyst, this paper takes a comprehensive look at how well current LLMs and new LRMs do on PlanBench. As we shall see, while o1's performance is a quantum improvement on the benchmark, outpacing the competition, it is still far from saturating it. This improvement also brings to the fore questions about accuracy, efficiency, and guarantees which must be considered before deploying such systems.

Related papers

• Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads [104.9566359759396]
  We propose a lightweight alternative for step-level reasoning verification based on data-driven uncertainty scores.<n>Our findings suggest that the internal states of LLMs encode their uncertainty and can serve as reliable signals for reasoning verification.
  arXiv  Detail & Related papers  (2025-11-09T03:38:29Z)
• AthenaBench: A Dynamic Benchmark for Evaluating LLMs in Cyber Threat Intelligence [4.077787659104315]
  Large Language Models (LLMs) have demonstrated strong capabilities in natural language reasoning, yet their application to Cyber Threat Intelligence (CTI) remains limited.<n>We extend CTIBench by developing AthenaBench, an enhanced benchmark that includes an improved dataset creation pipeline, duplicate removal, refined evaluation metrics, and a new task focused on risk mitigation strategies.<n>We evaluate twelve LLMs, including state-of-the-art proprietary models such as GPT-5 and Gemini-2.5 Pro, alongside seven open-source models from the LLaMA and Qwen families.
  arXiv  Detail & Related papers  (2025-11-03T01:45:29Z)
• $\ exttt{LLINBO}$: Trustworthy LLM-in-the-Loop Bayesian Optimization [1.9311784849535178]
  Large Language Models (LLMs) have shown remarkable adaptability in low-data regimes.<n>We propose LLINBO: LLM-in-the-Loop BO, a hybrid framework for BO that combines LLMs with statistical surrogate experts.<n>We end the paper with a real-life proof-of-concept in the context of 3D printing.
  arXiv  Detail & Related papers  (2025-05-20T15:54:48Z)
• Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation [55.21013307734612]
  AoPS-Instruct is a dataset of more than 600,000 high-quality QA pairs. LiveAoPSBench is an evolving evaluation set with timestamps, derived from the latest forum data. Our work presents a scalable approach to creating and maintaining large-scale, high-quality datasets for advanced math reasoning.
  arXiv  Detail & Related papers  (2025-01-24T06:39:38Z)
• LLMs Can Plan Only If We Tell Them [16.593590353705697]
  Large language models (LLMs) have demonstrated significant capabilities in natural language processing and reasoning. This paper investigates whether LLMs can independently generate long-horizon plans that rival human baselines.
  arXiv  Detail & Related papers  (2025-01-23T10:46:14Z)
• Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
  Large language models (LLMs) have significantly improved language understanding and generation capabilities. LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands. We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
  arXiv  Detail & Related papers  (2024-12-19T18:08:04Z)
• 7B Fully Open Source Moxin-LLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement [42.10844666788254]
  Moxin 7B is a fully open-source Large Language Models (LLMs) developed adhering to principles of open science, open source, open data, and open access. We release the pre-training code and configurations, training and fine-tuning datasets, and intermediate and final checkpoints. Experiments show that our models achieve superior performance in various evaluations such as zero-shot evaluation, few-shot evaluation, and CoT evaluation.
  arXiv  Detail & Related papers  (2024-12-08T02:01:46Z)
• Predicting Emergent Capabilities by Finetuning [98.9684114851891]
  We find that finetuning language models can shift the point in scaling at which emergence occurs towards less capable models. We validate this approach using four standard NLP benchmarks. We find that, in some cases, we can accurately predict whether models trained with up to 4x more compute have emerged.
  arXiv  Detail & Related papers  (2024-11-25T01:48:09Z)
• LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints [86.59857711385833]
  We introduce RealInstruct, the first benchmark designed to evaluate LLMs' ability to follow real-world multi-constrained instructions. To address the performance gap between open-source and proprietary models, we propose the Decompose, Critique and Refine (DeCRIM) self-correction pipeline. Our results show that DeCRIM improves Mistral's performance by 7.3% on RealInstruct and 8.0% on IFEval even with weak feedback.
  arXiv  Detail & Related papers  (2024-10-09T01:25:10Z)
• Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1 [15.863162558281616]
  We evaluate the planning capabilities of two LRMs (o1-preview and o1-mini) on both planning and scheduling benchmarks. We show that combining o1 models with external verifiers -- in a so-called LRM-Modulo system -- guarantees the correctness of the combined system's output.
  arXiv  Detail & Related papers  (2024-10-03T03:04:36Z)
• MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series [86.31735321970481]
  We open-source MAP-Neo, a bilingual language model with 7B parameters trained from scratch on 4.5T high-quality tokens. Our MAP-Neo is the first fully open-sourced bilingual LLM with comparable performance compared to existing state-of-the-art LLMs.
  arXiv  Detail & Related papers  (2024-05-29T17:57:16Z)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [70.09561665520043]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans. We provide theoretical analysis by extending advantage-weighted regression in reinforcement learning to multi-agent systems. Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)
• OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models [44.848642930797155]
  We release OpenMoE, a series of fully open-sourced and reproducible decoder-only Mixture-of-Experts (MoE) based large language models (LLMs) Our investigation confirms that MoE-based LLMs can offer a more favorable cost-effectiveness trade-off than dense LLMs. We find that routing decisions in MoE models are predominantly based on token IDs, with minimal context relevance.
  arXiv  Detail & Related papers  (2024-01-29T12:05:02Z)
• Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models [52.98743860365194]
  We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN) At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself. This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents.
  arXiv  Detail & Related papers  (2024-01-02T18:53:13Z)
• Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning [105.77733287326308]
  We evaluate 10 recent open-source LMMs from 3B up to 80B parameter scale, on 5 different axes; hallucinations, abstention, compositionality, explainability and instruction following. We explore the training-free in-context learning (ICL) as a solution, and study how it affects these limitations. Based on our ICL study, (3) we push ICL further and propose new multimodal ICL variants such as; Multitask-ICL, Chain-of-Hindsight-ICL, and Self-Correcting-ICL.
  arXiv  Detail & Related papers  (2023-10-01T12:02:59Z)
• On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark) [30.223130782579336]
  We develop a benchmark suite based on the kinds of domains employed in the International Planning Competition. We evaluate LLMs in three modes: autonomous, human-in-the-loop and human-in-the-loop. Our results show that LLM's ability to autonomously generate executable plans is quite meager, averaging only about 3% success rate.
  arXiv  Detail & Related papers  (2023-02-13T21:37:41Z)
• PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change [34.93870615625937]
  PlanBench is a benchmark suite based on the kinds of domains used in the automated planning community. PlanBench provides sufficient diversity in both the task domains and the specific planning capabilities.
  arXiv  Detail & Related papers  (2022-06-21T16:15:27Z)

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.