Papers Math
“Math” 태그가 달린 논문 1,596편 · 필터 해제
One RL to See Them All: Visual Triple Unified Reinforcement Learning
Reinforcement learning (RL) has significantly advanced the reasoning capabilities of vision-language models (VLMs). However, the use of RL beyond reasoning tasks remains largely unexplored, especially for perceptioninten…
AllMathOptical Character Recognition (OCR)Reinforcement Learning (RL)+1Value-Guided Search for Efficient Chain-of-Thought Reasoning
In this paper, we propose a simple and efficient method for value model training on long-context reasoning traces. Compared to existing process reward models (PRMs), our method does not require a fine-grained notion of "…
MathVideoGameBench: Can Vision-Language Models complete popular video games?
Vision-language models (VLMs) have achieved strong results on coding and math benchmarks that are challenging for humans, yet their ability to perform tasks that come naturally to humans--such as perception, spatial navi…
MathDecoupled Visual Interpretation and Linguistic Reasoning for Math Problem Solving
Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understandi…
Language ModelingLanguage ModellingMathMore Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
Test-time compute has empowered multimodal large language models to generate extended reasoning chains, yielding strong performance on tasks such as multimodal math reasoning. However, this improved reasoning ability oft…
DiagnosticHallucinationMathMultimodal Reasoning+1Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
Unlearning in large language models (LLMs) is intended to remove the influence of specific data, yet current evaluations rely heavily on token-level metrics such as accuracy and perplexity. We show that these metrics can…
DiagnosticMachine UnlearningMathX-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs
LLM-based multi-agent systems (MAS) extend the capabilities of single LLMs by enabling cooperation among multiple specialized agents. However, most existing MAS frameworks rely on a single LLM to drive all agents, constr…
ChatbotMathIncremental Sequence Classification with Temporal Consistency
We address the problem of incremental sequence classification, where predictions are updated as new elements in the sequence are revealed. Drawing on temporal-difference learning from reinforcement learning, we identify …
ClassificationLanguage ModelingLanguage ModellingLarge Language Model+3SATURN: SAT-based Reinforcement Learning to Unleash Language Model Reasoning
How to design reinforcement learning (RL) tasks that effectively unleash the reasoning capability of large language models (LLMs) remains an open question. Existing RL tasks (e.g., math, programming, and constructing rea…
Language ModelingLanguage ModellingMathReinforcement Learning (RL)AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
Despite recent progress in large-scale reinforcement learning (RL) for reasoning, the training recipe for building high-performing reasoning models remains elusive. Key implementation details of frontier models, such as …
Mathreinforcement-learningReinforcement LearningReinforcement Learning (RL)WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
While reinforcement learning (RL) has demonstrated remarkable success in enhancing large language models (LLMs), it has primarily focused on single-turn tasks such as solving math problems. Training effective web agents …
MathReinforcement Learning (RL)RBench-V: A Primary Assessment for Visual Reasoning Models with Multi-modal Outputs
The rapid advancement of native multi-modal models and omni-models, exemplified by GPT-4o, Gemini, and o3, with their capability to process and generate content across modalities such as text and images, marks a signific…
Image ManipulationMathVisual ReasoningEquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning
Large Language Models (LLMs) excel at complex reasoning through search algorithms, yet current strategies often suffer from massive token consumption due to redundant exploration of semantically equivalent steps. Existin…
GSM8KMathMathematical ReasoningSemantic Similarity+1Veracity Bias and Beyond: Uncovering LLMs' Hidden Beliefs in Problem-Solving Reasoning
Despite LLMs' explicit alignment against demographic stereotypes, they have been shown to exhibit biases under various social contexts. In this work, we find that LLMs exhibit concerning biases in how they associate solu…
AttributeMathConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models
Large language models excel at complex tasks by breaking down problems into structured reasoning steps. However, reasoning traces often extend beyond reaching a correct answer, causing wasted computation, reduced readabi…
Large Language ModelMathreinforcement-learningReinforcement LearningCan LLMs $\textit{understand}$ Math? -- Exploring the Pitfalls in Mathematical Reasoning
Large language models (LLMs) demonstrate considerable potential in various natural language tasks but face significant challenges in mathematical reasoning, particularly in executing precise, multi-step logic. However, c…
MathMathematical ReasoningThe Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
Entropy minimization (EM) trains the model to concentrate even more probability mass on its most confident outputs. We show that this simple objective alone, without any labeled data, can substantially improve large lang…
MathModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges
Recent progress in large language models (LLMs) has enabled substantial advances in solving mathematical problems. However, existing benchmarks often fail to reflect the complexity of real-world problems, which demand op…
MathvalidRL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
Reinforcement learning (RL) has recently emerged as a compelling approach for enhancing the reasoning capabilities of large language models (LLMs), where an LLM generator serves as a policy guided by a verifier (reward m…
MathMathematical ReasoningReinforcement Learning (RL)Learning to Rank Chain-of-Thought: An Energy-Based Approach with Outcome Supervision
Mathematical reasoning presents a significant challenge for Large Language Models (LLMs), often requiring robust multi step logical consistency. While Chain of Thought (CoT) prompting elicits reasoning steps, it doesn't …
GSM8KLearning-To-RankMathMathematical Reasoning