Related papers: Compass-Thinker-7B Technical Report

Language model pretraining with next token prediction has proved effective for scaling compute but is limited to the amount of available training data. Scaling reinforcement learning (RL) unlocks a new axis for the continued improvement of…

Process Reward Models (PRMs) have recently emerged as a powerful framework for supervising intermediate reasoning steps in large language models (LLMs). Previous PRMs are primarily trained on model final output responses and struggle to…

Retrieval-Augmented Generation (RAG) has been shown to enhance the factual accuracy of Large Language Models (LLMs), but existing methods often suffer from limited reasoning capabilities in effectively using the retrieved evidence,…

Tool-integrated reasoning (TIR) has emerged as a dominant paradigm for mathematical problem solving in language models, combining natural language (NL) reasoning with code execution. However, this interleaved setup has three key…

Reinforcement learning exhibits potential in enhancing the reasoning abilities of large language models, yet it is hard to scale for the low sample efficiency during the rollout phase. Existing methods attempt to improve efficiency by…

This study investigates the performance of the DeepSeek R1 language model on 30 challenging mathematical problems derived from the MATH dataset, problems that previously proved unsolvable by other models under time constraints. Unlike prior…

Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability. Yet, outcome-based reward often incentivizes models to be overconfident, leading to…

We aim to improve the reasoning capabilities of language models via reinforcement learning (RL). Recent RL post-trained models like DeepSeek-R1 have demonstrated reasoning abilities on mathematical and coding tasks. However, prior studies…

Compiler auto-tuning optimizes pass sequences to improve performance metrics such as Intermediate Representation (IR) instruction count. Although recent advances leveraging Large Language Models (LLMs) have shown promise in automating…

Recently, large language models (LLMs) have shown remarkable reasoning capabilities via large-scale reinforcement learning (RL). However, leveraging the RL algorithm to empower effective multi-tool collaborative reasoning in LLMs remains an…

Accurate process supervision remains a critical challenge for long-horizon robotic manipulation. A primary bottleneck is that current video MLLMs, trained primarily under a Supervised Fine-Tuning (SFT) paradigm, function as passive…

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising approach for training reasoning language models (RLMs) by leveraging supervision from verifiers. Although verifier implementation is easier than solution…

Recent breakthroughs in generative reasoning have fundamentally reshaped how large language models (LLMs) address complex tasks, enabling them to dynamically retrieve, refine, and organize information into coherent multi-step reasoning…

Recent advancements in large language models (LLMs) have demonstrated substantial progress in reasoning capabilities, such as DeepSeek-R1, which leverages rule-based reinforcement learning to enhance logical reasoning significantly.…

Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason, exhibiting promising performance in solving complex tasks. However, their deliberative reasoning process leads…

Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to…

Test-time scaling offers a promising path to improve LLM reasoning by utilizing more compute at inference time; however, the true promise of this paradigm lies in extrapolation (i.e., improvement in performance on hard problems as LLMs keep…

Retrosynthesis planning, essential in organic synthesis and drug discovery, has greatly benefited from recent AI-driven advancements. Nevertheless, existing methods frequently face limitations in both applicability and explainability.…

Recent advancements in large language models (LLMs) have demonstrated impressive chain-of-thought reasoning capabilities, with reinforcement learning (RL) playing a crucial role in this progress. While "aha moment" patterns--where models…