6 papers
Scaling Reasoning Tokens via RL and Parallel Thinking: Evidence From Competitive Programming
Qianfan Zhang, Tianyu Guo, Xuandi Ren +4
We study how to scale reasoning token budgets for competitive programming through two complementary approaches: training-time reinforcement learning (RL) and test-time parallel thi…
Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers
Ran Xin, Zeyu Zheng, Yanchen Nie +2
The integration of Large Language Models (LLMs) into automated theorem proving has shown immense promise, yet is fundamentally constrained by challenges in scaling up both training…
BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving
Ran Xin, Chenguang Xi, Jie Yang +6
Recent advancements in large language models (LLMs) have spurred growing interest in automatic theorem proving using Lean4, where effective tree search methods are crucial for navi…
Seed-Coder: Let the Code Model Curate Data for Itself
ByteDance Seed, Yuyu Zhang, Jing Su +24
Code data in large language model (LLM) pretraining is recognized crucial not only for code-related tasks but also for enhancing general intelligence of LLMs. Current open-source L…
From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs
Jiliang Ni, Jiachen Pu, Zhongyi Yang +7
Large Language Models (LLMs) have significantly advanced artificial intelligence by optimizing traditional Natural Language Processing (NLP) workflows, facilitating their integrati…
IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation
Fan Lin, Shuyi Xie, Yong Dai +7
As Large Language Models (LLMs) grow increasingly adept at managing complex tasks, the evaluation set must keep pace with these advancements to ensure it remains sufficiently discr…