Papers Mathematical Reasoning
“Mathematical Reasoning” 태그가 달린 논문 1,929편 · 필터 해제
From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning
Plane geometry remains a significant challenge in AI, requiring the integration of visual perception and mathematical reasoning. While Large Multimodal Models (LMMs) naturally handle visuo-linguistic inputs, they are oft…
Mathematical ReasoningWhich Tokens Should SFT Actually Learn? A Token-Trimming Perspective on Mathematical Reasoning
Supervised fine-tuning (SFT) applies a uniform cross-entropy loss to all target tokens, even though different tokens provide unequal learning signals for mathematical reasoning. This uniform treatment can over-sharpen al…
Mathematical ReasoningDifficulty-Adaptive Tree-Structured Policy Optimization for Expanding Reasoning Coverage in RLVR
Reinforcement Learning with Verifiable Rewards (RLVR) has been central to the recent success of Large Reasoning Models. However, while RLVR significantly improves single-sample accuracy, it often fails to expand the mode…
Mathematical ReasoningReinforcement LearningRISE: Recursive Improvement via Self-Extrapolating Policy Distillation
On-policy distillation (OPD) provides dense, per-token supervision for language model post-training, but its effectiveness is bottlenecked by teacher quality: external teachers suffer from distribution mismatch, while se…
Mathematical ReasoningCode GenerationDo LLMs Exhibit Coherent Knowledge Structures in Mathematical Reasoning? A Perspective from Knowledge Space Theory
Human knowledge is inherently structured and interdependent: mastery of a concept requires prior mastery of its prerequisites, a principle formalized by Knowledge Space Theory (KST). While LLMs achieve strong performance…
Mathematical ReasoningFirst Things First: Teaching LLM-Based Agents to Prioritize Must-Haves before Nice-to-Haves
Recent progress in multimodal large language models (MLLMs) has fueled significant enthusiasm in their potential to act as autonomous agents for real-world tasks. However, scenarios requiring agents to fulfill users' com…
Reinforcement LearningMathematical ReasoningExtremely Sparse Supervision Incentivizes Reasoning Ability
Large language models demonstrate increasingly strong reasoning capabilities through effective post-training. Yet, prevailing post-training methods optimize over massive numbers of tokens, implicitly assuming that effect…
Reinforcement LearningMathematical ReasoningFlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience
A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers provide reliable yet sparse supervision, while dense same-model guidance can reinforce false confidence …
Mathematical ReasoningDiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory
Self-play is an effective paradigm for language-model self-evolution, but without guidance, solver performance can plateau or decline across rounds. Unguided methods steer question generation with signals such as difficu…
Mathematical ReasoningQuestion GenerationMore Capable, Less Faithful: A Multilingual Analysis of Mathematical (Un)Solvability Detection in LLMs
Solvability detection is one of the most challenging aspects of mathematical reasoning for Large Language Models (LLMs). While prior work has studied this capability extensively, these analyses have been limited to Engli…
Mathematical ReasoningReactivating Test-Time Scaling for Plane Geometry Problem Solving
Plane geometry problem (PGP) solving has become a critical benchmark for multimodal reasoning because it requires accurate visual perception and precise multi-step symbolic deduction. Although test-time scaling (TTS) has…
Mathematical ReasoningMultimodal ReasoningVisual GroundingWHALE: A Simple Recipe for Joint Harness-Weight Optimization
Agent performance depends jointly on the model parameters and the executable harness code that manages context and control flow. Optimizing either component in isolation can leave the system bottlenecked by its frozen co…
Mathematical ReasoningQuestion AnsweringDARTS: Decoder-Aware Representation Tuning via Surgery for Model Merging
Model merging combines multiple task-specific fine-tuned LLMs into a single multi-task model without additional training. However, merged models are known to suffer from representation bias: systematic drift between the …
Mathematical ReasoningInstruction FollowingCode GenerationNL2AGBench: Benchmarking LLM Auto-Formalization for AlphaGeometry
Recent advances in large language models (LLMs) have demonstrated strong capabilities in natural language understanding and mathematical reasoning. However, their ability to translate informal mathematical problems into …
Natural Language UnderstandingMathematical ReasoningLearning to Use Tools: Reinforcement Learning for Tool-Integrated Mathematical Reasoning
Current large language models (LLMs) increasingly benefit from external tool integration, especially for tasks requiring reliable computation and verification. Motivated by this, we study calculator tool calling for impr…
Reinforcement LearningMathematical ReasoningTTPO: Test-Time Policy Optimization
Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Self-Distillation (OPSD), have driven rapid progress in mathematical reasoning for large language models, yet their reliance on gr…
Mathematical ReasoningReinforcement LearningFrom Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities
Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence. However, most existing math benchmarks evaluate only final answers. This outcome-oriented e…
Mathematical ReasoningINSPIRE: An Internalize-Then-Improve Approach for Example-Driven Mathematical Reasoning
Mathematical reasoning has seen rapid progress in large language models (LLMs), yet existing methods optimize predominantly for final-answer correctness, raising the question whether models truly internalize mathematical…
Mathematical ReasoningProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs
Multi-agent large language model (LLM) workflows have emerged as a powerful paradigm for solving complex, open-ended tasks through collaborative reasoning among specialized LLM agents, but they incur substantial operatin…
Mathematical ReasoningQuestion AnsweringCode GenerationOne Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation
On-policy distillation trains a language model on its own generations while a teacher scores them token by token. It combines the dense supervision of imitation learning with the on-policy sampling of reinforcement learn…
Mathematical ReasoningReinforcement Learning