Zobrazeno 1 - 10
of 48 947
pro vyhledávání: '"TREE-SEARCH"'
Autor:
Yao, Huanjin, Huang, Jiaxing, Wu, Wenhao, Zhang, Jingyi, Wang, Yibo, Liu, Shunyu, Wang, Yingjie, Song, Yuxin, Feng, Haocheng, Shen, Li, Tao, Dacheng
In this work, we aim to develop an MLLM that understands and solves questions by learning to create each intermediate step of the reasoning involved till the final answer. To this end, we propose Collective Monte Carlo Tree Search (CoMCTS), a new lea
Externí odkaz:
http://arxiv.org/abs/2412.18319
Scaling laws for inference compute in multi-agent systems remain under-explored compared to single-agent scenarios. This work aims to bridge this gap by investigating the problem of data synthesis through multi-agent sampling, where synthetic respons
Externí odkaz:
http://arxiv.org/abs/2412.17061
Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning
Despite recent advances in large language models, open-source models often struggle to consistently perform well on complex reasoning tasks. Existing ensemble methods, whether applied at the token or output levels, fail to address these challenges. I
Externí odkaz:
http://arxiv.org/abs/2412.15797
Autor:
Li, Junyi, Ng, Hwee Tou
Despite their outstanding capabilities, large language models (LLMs) are prone to hallucination and producing factually incorrect information. This challenge has spurred efforts in attributed text generation, which prompts LLMs to generate content wi
Externí odkaz:
http://arxiv.org/abs/2412.14860
Competition-level code generation tasks pose significant challenges for current state-of-the-art large language models (LLMs). For example, on the LiveCodeBench-Hard dataset, models such as O1-Mini and O1-Preview achieve pass@1 rates of only 0.366 an
Externí odkaz:
http://arxiv.org/abs/2412.12544
Autor:
Cheng, Jiale, Liu, Xiao, Wang, Cunxiang, Gu, Xiaotao, Lu, Yida, Zhang, Dan, Dong, Yuxiao, Tang, Jie, Wang, Hongning, Huang, Minlie
Instruction-following is a fundamental capability of language models, requiring the model to recognize even the most subtle requirements in the instructions and accurately reflect them in its output. Such an ability is well-suited for and often optim
Externí odkaz:
http://arxiv.org/abs/2412.11605
Publikováno v:
Science Robotics, 4 Dec 2024, Vol 9, Issue 97
The ability of a robot to plan complex behaviors with real-time computation, rather than adhering to predesigned or offline-learned routines, alleviates the need for specialized algorithms or training for each problem instance. Monte Carlo Tree Searc
Externí odkaz:
http://arxiv.org/abs/2412.11270
Autor:
Jiang, Jinhao, Chen, Zhipeng, Min, Yingqian, Chen, Jie, Cheng, Xiaoxue, Wang, Jiapeng, Tang, Yiru, Sun, Haoxiang, Deng, Jia, Zhao, Wayne Xin, Liu, Zheng, Yan, Dong, Xie, Jian, Wang, Zhongyuan, Wen, Ji-Rong
Recently, test-time scaling has garnered significant attention from the research community, largely due to the substantial advancements of the o1 model released by OpenAI. By allocating more computational resources during the inference phase, large l
Externí odkaz:
http://arxiv.org/abs/2411.11694
Large language models (LLMs) have demonstrated their remarkable capacity across a variety of tasks. However, reasoning remains a challenge for LLMs. To improve LLMs' reasoning ability, process supervision has proven to be better than outcome supervis
Externí odkaz:
http://arxiv.org/abs/2501.01478
We introduce HunyuanProver, an language model finetuned from the Hunyuan 7B for interactive automatic theorem proving with LEAN4. To alleviate the data sparsity issue, we design a scalable framework to iterative synthesize data with low cost. Besides
Externí odkaz:
http://arxiv.org/abs/2412.20735