Mathematical Reasoning

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 226–250 of 805 papers

Title	Date	Tasks	Status	Hype
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks	Mar 27, 2025	Imitation LearningMathematical Reasoning	CodeCode Available	2
MATHGLANCE: Multimodal Large Language Models Do Not Know Where to Look in Mathematical Diagrams	Mar 26, 2025	Mathematical ReasoningObject Counting	—Unverified	0
Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence	Mar 26, 2025	Mathematical Reasoning	CodeCode Available	0
RL-finetuning LLMs from on- and off-policy data with a single algorithm	Mar 25, 2025	Mathematical Reasoning	—Unverified	0
Learning to chain-of-thought with Jensen's evidence lower bound	Mar 25, 2025	Mathematical Reasoningreinforcement-learning	—Unverified	0
Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking	Mar 25, 2025	In-Context LearningMathematical Reasoning	—Unverified	0
Process or Result? Manipulated Ending Tokens Can Mislead Reasoning LLMs to Ignore the Correct Reasoning Steps	Mar 25, 2025	Mathematical Reasoning	—Unverified	0
CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning	Mar 24, 2025	Language ModelingLanguage Modelling	—Unverified	0
Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training	Mar 24, 2025	DiversityLarge Language Model	CodeCode Available	1
Lost in Cultural Translation: Do LLMs Struggle with Math Across Cultural Contexts?	Mar 23, 2025	GSM8KMath	CodeCode Available	0
A Survey on Mathematical Reasoning and Optimization with Large Language Models	Mar 22, 2025	Automated Theorem ProvingHeuristic Search	CodeCode Available	0
Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't	Mar 20, 2025	Mathematical ReasoningReinforcement Learning (RL)	CodeCode Available	3
MathFusion: Enhancing Mathematic Problem-solving of LLM through Instruction Fusion	Mar 20, 2025	Data AugmentationMathematical Problem-Solving	CodeCode Available	1
MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer	Mar 19, 2025	Answer GenerationMathematical Reasoning	CodeCode Available	1
Temporal Consistency for LLM Reasoning Process Error Identification	Mar 18, 2025	Mathematical Reasoning	CodeCode Available	0
Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation	Mar 17, 2025	Mathematical ReasoningReinforcement Learning (RL)	CodeCode Available	1
Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning	Mar 17, 2025	Mathematical ReasoningMultimodal Reasoning	—Unverified	0
Pensez: Less Data, Better Reasoning -- Rethinking French LLM	Mar 17, 2025	Large Language ModelMath	—Unverified	0
Reliable and Efficient Amortized Model-based Evaluation	Mar 17, 2025	DiagnosticMathematical Reasoning	—Unverified	0
Evaluating Mathematical Reasoning Across Large Language Models: A Fine-Grained Approach	Mar 13, 2025	Formal LogicMathematical Reasoning	—Unverified	0
VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models	Mar 10, 2025	Binary ClassificationHallucination	CodeCode Available	0
Implicit Reasoning in Transformers is Reasoning through Shortcuts	Mar 10, 2025	Mathematical Reasoning	CodeCode Available	1
RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs	Mar 8, 2025	Instruction FollowingMathematical Reasoning	CodeCode Available	2
Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?	Mar 8, 2025	Mathematical ReasoningMultimodal Reasoning	CodeCode Available	2
Speculative Decoding for Multi-Sample Inference	Mar 7, 2025	Mathematical Reasoning	—Unverified	0

Show:10 25 50

← PrevPage 10 of 33Next →

All datasets AIME24 FrontierMath Lila (IID)Lila (OOD)PGPS9K AMC23 GeoQA Math500 UniGeo UniGeo (PRV)

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Xolver	Acc	94.4	—	Unverified
2	DeepSeek-r1	Acc	79.8	—	Unverified
3	Openai-o1	Acc	74.4	—	Unverified
4	Openai-o1-mini	Acc	70	—	Unverified
5	Search-o1	Acc	56.7	—	Unverified
6	s1-32B	Acc	56.7	—	Unverified
7	Openai-o1-preview	Acc	44.6	—	Unverified
8	Qwen2.5-72B-Instruct	Acc	23.3	—	Unverified
9	Claude3.5-Sonnet	Acc	16	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	o3	Accuracy	0.25	—	Unverified
2	Gemini 1.5 Pro (002)	Accuracy	0.02	—	Unverified
3	GPT-4o	Accuracy	0.01	—	Unverified
4	o1-mini	Accuracy	0.01	—	Unverified
5	o1-preview	Accuracy	0.01	—	Unverified
6	Claude 3.5 Sonnet	Accuracy	0.01	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Codex (Few-Shot, 175B)	Accuracy	0.6	—	Unverified
2	Bhāskara-P (Fine-tuned, 2.7B)	Accuracy	0.48	—	Unverified
3	Neo-P (Fine-tuned, 2.7B)	Accuracy	0.39	—	Unverified
4	GPT-3 (Few-Shot, 175B)	Accuracy	0.38	—	Unverified
5	Bhāskara-A (Fine-tuned, 2.7B)	Accuracy	0.25	—	Unverified
6	Neo-A (Fine-tuned, 2.7B)	Accuracy	0.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Codex (Few-Shot, 175B)	Accuracy	0.59	—	Unverified
2	Bhāskara-P (Fine-tuned, 2.7B)	Accuracy	0.45	—	Unverified
3	GPT-3 (Few-Shot, 175B)	Accuracy	0.38	—	Unverified
4	Bhāskara-A (Fine-tuned, 2.7B)	Accuracy	0.27	—	Unverified
5	Neo-P (Fine-tuned, 2.7B)	Accuracy	0.24	—	Unverified
6	Neo-A (Fine-tuned, 2.7B)	Accuracy	0.18	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GOLD	Completion accuracy	65.8	—	Unverified
2	PGPSNet	Completion accuracy	62.7	—	Unverified
3	GAPS	Completion accuracy	61.2	—	Unverified
4	Inter-GPS	Completion accuracy	59.8	—	Unverified
5	Geoformer	Completion accuracy	35.6	—	Unverified
6	NGS	Completion accuracy	34.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	QWQ-32B-preview	Acc	82.5	—	Unverified
2	Math-Master	Acc	82	—	Unverified
3	Qwen2.5-Math-7B-instruct	Acc	62.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GOLD	Accuracy (%)	75.2	—	Unverified
2	GAPS	Accuracy (%)	67.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Search-o1	Acc	86.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GOLD	Accuracy (%)	98.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GAPS	Accuracy (%)	97.5	—	Unverified