paper-with-me

Papers

DeepThink3D: Enhancing Large Language Models with Programmatic Reasoning in Complex 3D Situated Reasoning Tasks

2025-08-21 · Jiayi Song, Rui Wan, Lipeng Ma, Weidong Yang, Qingyuan Zhou, Yixuan Li, Ben Fei arxiv

This work enhances the ability of large language models (LLMs) to perform complex reasoning in 3D scenes. Recent work has addressed the 3D situated reasoning task by invoking tool usage through large language models. Large language models call tools via APIs and integrate the generated programs through a chain of thought to solve problems based on the program results. However, due to the simplicity of the questions in the dataset, the generated program reasoning chains are relatively short. To solve this main challenge, in this paper, we introduce DeepThink3D to enhance the tool usage of LLMs in complex 3D situated reasoning tasks. Our work proposes a combinatorial and iterative evolutionary approach on the SQA3D benchmark to generate more complex questions. Building on this foundation, we fine-tune the large language model to make it more proficient in using 3D tools. By employing Direct Preference Optimization (DPO), we directly optimize the toolchain strategies generated by models, thereby enhancing their accuracy in complex tasks.

📄 PDF Abstract BibTeX arXiv:2508.15548

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models

2025-10-31 · Cheng Yin, Yankai Lin, Wang Xu, Sikyuen Tam 외 arxiv

Does Chain-of-Thought (CoT) reasoning genuinely improve Vision-Language-Action (VLA) models, or does it merely add overhead? Existing CoT-VLA systems report limited and inconsistent gains, yet no prior work has rigorousl…

Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models

2026-04-20 · Xiang He, Chenxing Li, Jinting Wang, Yan Rong 외 arxiv

Large Audio-Language Models (LALMs) have made significant progress in audio understanding, yet they primarily operate as perception-and-answer systems without explicit reasoning processes. Existing methods for enhancing …

Reinforcement Learning

OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation

2026-05-14 · Shang Zhou, Wenhao Chai, Kaiyuan Liu, Huanzhi Mao 외 arxiv

Test-time compute scaling is a primary axis for improving LLM reasoning. Existing methods primarily scale depth by extending a single reasoning trace. Scaling breadth by sampling multiple candidates in parallel is straig…

VProChart: Answering Chart Question through Visual Perception Alignment Agent and Programmatic Solution Reasoning

2024-09-03 · Muye Huang, Lingling Zhang, Lai Han, Wenjun Wu 외

Charts are widely used for data visualization across various fields, including education, research, and business. Chart Question Answering (CQA) is an emerging task focused on the automatic interpretation and reasoning o…

Chart Question AnsweringData VisualizationLogical ReasoningQuestion Answering

DeepThink: Aligning Language Models with Domain-Specific User Intents

2025-02-08 · Yang Li, Mingxuan Luo, Yeyun Gong, Chen Lin 외

Supervised fine-tuning with synthesized instructions has been a common practice for adapting LLMs to domain-specific QA tasks. However, the synthesized instructions deviate from real user questions and expected answers. …

RAG