Papers with Code 아카이브

Mathematical Reasoning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

7

평가표

11

보존된 평가 기록

41

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/sunblaze-ucb/reasoning_ladder

공식 코드

Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT?

https://github.com/sunnynexus/search-o1

공식 코드

Search-o1: Agentic Search-Enhanced Large Reasoning Models

https://github.com/symoon11/guided-stream-of-search

공식 코드

Guided Stream of Search: Learning to Better Search with Language Models via Optimal Path Guidance

https://github.com/tenghaohuang/pluto

공식 코드

Planning and Editing What You Retrieve for Enhanced Tool Learning

https://github.com/tengxiao1/gsil

공식 코드

How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective

https://github.com/the-jb/athena-math

공식 코드

ATHENA: Mathematical Reasoning with Thought Expansion

https://github.com/thu-coai/codeplan

공식 코드

Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning

https://github.com/thudm/sciglm

공식 코드

SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models

https://github.com/tianduowang/dpo-st

공식 코드

Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning

https://github.com/tianhongzxy/rlvr-decomposed

공식 코드

The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning

https://github.com/tim-siu/reinforcement-distillation

공식 코드

Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning

https://github.com/tingchenfu/mathif

공식 코드

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

https://github.com/tongjingqi/MathTrap

공식 코드

Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning

https://github.com/tongxiao2002/dualgeosolver

공식 코드

Learning to Solve Geometry Problems via Simulating Human Dual-Reasoning Process

https://github.com/tonywu95/lime

공식 코드

LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning

https://github.com/trotsky1997/mathblackbox

공식 코드

Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B

https://github.com/twni2016/llm-reasoning-uft

공식 코드

Teaching Large Language Models to Reason through Learning and Forgetting

https://github.com/txc701/open-source-code-for-ai4m

공식 코드

Mathematical Formalized Problem Solving and Theorem Proving in Different Fields in Lean 4

https://github.com/umass-ml4ed/mathgpt

공식 코드

Tree-Based Representation and Generation of Natural and Mathematical Language

https://github.com/umass-ml4ed/reticl

공식 코드

RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning

https://github.com/unimodal4reasoning/geox

공식 코드

GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training

https://github.com/uranium11010/lemma

공식 코드

LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions

https://github.com/usail-hkust/llm-mm-agent

공식 코드

MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem

https://github.com/uscnlp-lime/verl

공식 코드

Efficient Reinforcement Finetuning via Adaptive Curriculum Learning

https://github.com/utmathgroup/utmath

공식 코드

UTMath: Math Evaluation with Unit Test via Reasoning-to-Coding Thoughts

https://github.com/veds12/ai_assisted_questions

공식 코드

AI-Assisted Generation of Difficult Math Questions

https://github.com/vernontoh/veritymath

공식 코드

VerityMath: Advancing Mathematical Reasoning by Self-Verification Through Unit Consistency

https://github.com/visual-agent/deepeyes

공식 코드

DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning

https://github.com/vlgiitr/llm-math

공식 코드

Give me a hint: Can LLMs take a hint to solve math problems?

https://github.com/volcengine/verl

공식 코드

ReTool: Reinforcement Learning for Strategic Tool Use in LLMs

https://github.com/wangitu/ada-instruct

공식 코드

Ada-Instruct: Adapting Instruction Generators for Complex Reasoning

https://github.com/we-math/we-math

공식 코드

We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?

https://github.com/weiji-feng/mad-eval

공식 코드

Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition

https://github.com/whu-zqh/dup

공식 코드

Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems

https://github.com/wind-2375-like/misinfo-prop

공식 코드

Unraveling Misinformation Propagation in LLM Reasoning

https://github.com/wlchen0206/llm-sp

공식 코드

Do LLM Evaluators Prefer Themselves for a Reason?

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.