paper-with-me

홈 › Papers

SmallPlan: Leverage Small Language Models for Sequential Path Planning with Simulation-Powered, LLM-Guided Distillation

2025-05-01 · Quang P. M. Pham, Khoi T. N. Nguyen, Nhi H. Doan, Cuong A. Pham, Kentaro Inui, Dezhen Song

Efficient path planning in robotics, particularly within large-scale, dynamic environments, remains a significant hurdle. While Large Language Models (LLMs) offer strong reasoning capabilities, their high computational cost and limited adaptability in dynamic scenarios hinder real-time deployment on edge devices. We present SmallPlan -- a novel framework leveraging LLMs as teacher models to train lightweight Small Language Models (SLMs) for high-level path planning tasks. In SmallPlan, the SLMs provide optimal action sequences to navigate across scene graphs that compactly represent full-scaled 3D scenes. The SLMs are trained in a simulation-powered, interleaved manner with LLM-guided supervised fine-tuning (SFT) and reinforcement learning (RL). This strategy not only enables SLMs to successfully complete navigation tasks but also makes them aware of important factors like travel distance and number of trials. Through experiments, we demonstrate that the fine-tuned SLMs perform competitively with larger models like GPT-4o on sequential path planning, without suffering from hallucination and overfitting. SmallPlan is resource-efficient, making it well-suited for edge-device deployment and advancing practical autonomous robotics. Our source code is available here: https://github.com/quangpham2006/SmallPlan

📄 PDF Abstract BibTeX arXiv:2505.00831

Code (1)

quangpham2006/SmallPlan 공식 구현 pytorch

Tasks

HallucinationNavigateReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Travel 설명 없음
AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

Can Small Language Models be Good Reasoners for Sequential Recommendation?

2024-03-07 · Yuling Wang, Changxin Tian, Binbin Hu, Yanhua Yu 외

Large language models (LLMs) open up new horizons for sequential recommendations, owing to their remarkable language comprehension and generation capabilities. However, there are still numerous challenges that should be …

Knowledge DistillationRecommendation SystemsSequential Recommendation

Twice Sequential Monte Carlo for Tree Search

2025-11-18 · Yaniv Oren, Joery A. de Vries, Pascal R. van der Vaart, Matthijs T. J. Spaan 외 arxiv

Model-based reinforcement learning (RL) methods that leverage search are responsible for many milestone breakthroughs in RL. Sequential Monte Carlo (SMC) recently emerged as an alternative to the Monte Carlo Tree Search …

Reinforcement Learning

SLMRec: Distilling Large Language Models into Small for Sequential Recommendation

2024-05-28 · Wujiang Xu, Qitian Wu, Zujie Liang, Jiaojiao Han 외

Sequential Recommendation (SR) task involves predicting the next item a user is likely to interact with, given their past interactions. The SR models examine the sequence of a user's actions to discern more complex behav…

Knowledge DistillationLanguage ModelingLanguage ModellingLarge Language Model+3

STOC-TOT: Stochastic Tree-of-Thought with Constrained Decoding for Complex Reasoning in Multi-Hop Question Answering

2024-07-04 · Zhenyu Bi, Daniel Hajialigol, Zhongkai Sun, Jie Hao 외

Multi-hop question answering (MHQA) requires a model to retrieve and integrate information from multiple passages to answer a complex question. Recent systems leverage the power of large language models and integrate evi…

HallucinationMulti-hop Question AnsweringQuestion Answering

Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision Making

2023-05-27 · Xuanjie Fang, Sijie Cheng, Yang Liu, Wei Wang

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a de…

Adversarial AttackDecision MakingSemantic SimilaritySemantic Textual Similarity+1