Papers Math
“Math” 태그가 달린 논문 1,596편 · 필터 해제
Steering LLM Thinking with Budget Guidance
Recent deep-thinking large language models often reason extensively to improve performance, but such lengthy reasoning is not always desirable, as it incurs excessive inference costs with disproportionate performance gai…
MathAceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy
In this work, we investigate the synergy between supervised fine-tuning (SFT) and reinforcement learning (RL) in developing strong reasoning models. We begin by curating the SFT training data through two scaling strategi…
MathReinforcement Learning (RL)Direct Reasoning Optimization: LLMs Can Reward And Refine Their Own Reasoning for Open-Ended Tasks
Recent advances in Large Language Models (LLMs) have showcased impressive reasoning abilities in structured tasks like mathematics and programming, largely driven by Reinforcement Learning with Verifiable Rewards (RLVR),…
FormMathTreeRL: LLM Reinforcement Learning with On-Policy Tree Search
Reinforcement learning (RL) with tree search has demonstrated superior performance in traditional reasoning tasks. Compared to conventional independent chain sampling strategies with outcome supervision, tree search enab…
Mathreinforcement-learningReinforcement LearningReinforcement Learning (RL)Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards
Reinforcement Learning from Verifiable Rewards (RLVR) has been widely adopted as the de facto method for enhancing the reasoning capabilities of large language models and has demonstrated notable success in verifiable do…
MathNavigateVGR: Visual Grounded Reasoning
In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias and is largely confined to math or scie…
Large Language ModelMathMultimodal Large Language ModelVisual ReasoningReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization
Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of Large Language Models (LLMs). However, these methods often suffer from overthinking, leading to unnecessarily …
MathSpurious Rewards: Rethinking Training Signals in RLVR
We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain models even with spurious rewards that have little, no, or even negative correlation with the correct…
MathMathematical ReasoningLearning a Continue-Thinking Token for Enhanced Test-Time Scaling
Test-time scaling has emerged as an effective approach for improving language model performance by utilizing additional compute at inference time. Recent studies have shown that overriding end-of-thinking tokens (e.g., r…
GSM8KMathTTT-Bench: A Benchmark for Evaluating Reasoning Ability with Simple and Novel Tic-Tac-Toe-style Games
Large reasoning models (LRMs) have demonstrated impressive reasoning capabilities across a broad range of tasks including Olympiad-level mathematical problems, indicating evidence of their complex reasoning abilities. Wh…
Logical ReasoningMathResa: Transparent Reasoning Models via SAEs
How cost-effectively can we elicit strong reasoning in language models by leveraging their underlying representations? We answer this question with Resa, a family of 1.5B reasoning models trained via a novel and efficien…
MathViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
Reinforcement learning (RL) has shown great effectiveness for fine-tuning large language models (LLMs) using tasks that are challenging yet easily verifiable, such as math reasoning or code generation. However, extending…
Code GenerationDiagnosticHallucinationImage Captioning+2Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning
Despite the rapid progress of multimodal large language models (MLLMs), they have largely overlooked the importance of visual processing. In a simple yet revealing experiment, we interestingly find that language-only mod…
Image CaptioningMathMathematical ReasoningVisual ReasoningRePO: Replay-Enhanced Policy Optimization
Reinforcement learning (RL) is vital for optimizing large language models (LLMs). Recent Group Relative Policy Optimization (GRPO) estimates advantages using multiple on-policy outputs per prompt, leading to high computa…
MathMathematical ReasoningReinforcement Learning (RL)LeanTutor: A Formally-Verified AI Tutor for Mathematical Proofs
We present LeanTutor, a Large Language Model (LLM)-based tutoring system for math proofs. LeanTutor interacts with the student in natural language, formally verifies student-written math proofs in Lean, generates correct…
Large Language ModelMathMathematical ProofsAbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
For Large Language Models (LLMs) to be reliably deployed in both everyday and high-stakes domains, knowing when not to answer is equally critical as answering correctly. Real-world user queries, which can be underspecifi…
MathReinforce LLM Reasoning through Multi-Agent Reflection
Leveraging more test-time computation has proven to be an effective way to boost the reasoning capabilities of large language models (LLMs). Among various methods, the verify-and-improve paradigm stands out for enabling …
MathOut-of-Distribution GeneralizationEnhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search
Small language models (SLMs) offer promising and efficient alternatives to large language models (LLMs). However, SLMs' limited capacity restricts their reasoning capabilities and makes them sensitive to prompt variation…
GSM8KMathmbppLearning to Reason Across Parallel Samples for LLM Reasoning
Scaling test-time compute brings substantial performance gains for large language models (LLMs). By sampling multiple answers and heuristically aggregate their answers (e.g., either through majority voting or using verif…
MathRe-RankingSwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning
Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for training large language models (LLMs) on complex reasoning tasks, such as mathematical problem solving. A prerequisite for the scalability of…
Knowledge DistillationMathMathematical Problem-Solving