Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | Li, Zongqian, Lv, Tengchao, Huang, Shaohan, Su, Yixuan, Sun, Qinzheng, Yin, Qiufeng, Xin, Ying, Li, Scarlett, Cui, Lei, Collier, Nigel, Wei, Furu |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
Documents similaires
Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models
par: Li, Zongqian, et autres
Publié: (2026)
par: Li, Zongqian, et autres
Publié: (2026)
A Survey on Prompt Tuning
par: Li, Zongqian, et autres
Publié: (2025)
par: Li, Zongqian, et autres
Publié: (2025)
PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning
par: Li, Zongqian, et autres
Publié: (2025)
par: Li, Zongqian, et autres
Publié: (2025)
500xCompressor: Generalized Prompt Compression for Large Language Models
par: Li, Zongqian, et autres
Publié: (2024)
par: Li, Zongqian, et autres
Publié: (2024)
MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark
par: Zhao, Qihao, et autres
Publié: (2024)
par: Zhao, Qihao, et autres
Publié: (2024)
RedStone: Curating General, Code, Math, and QA Data for Large Language Models
par: Chang, Yaoyao, et autres
Publié: (2024)
par: Chang, Yaoyao, et autres
Publié: (2024)
Prompt Compression for Large Language Models: A Survey
par: Li, Zongqian, et autres
Publié: (2024)
par: Li, Zongqian, et autres
Publié: (2024)
Flexi-LoRA with Input-Adaptive Ranks: Efficient Finetuning for Speech and Reasoning Tasks
par: Li, Zongqian, et autres
Publié: (2026)
par: Li, Zongqian, et autres
Publié: (2026)
ReasonGraph: Visualisation of Reasoning Paths
par: Li, Zongqian, et autres
Publié: (2025)
par: Li, Zongqian, et autres
Publié: (2025)
Code Aesthetics with Agentic Reward Feedback
par: Xiao, Bang, et autres
Publié: (2025)
par: Xiao, Bang, et autres
Publié: (2025)
BEYOND NATION: CARIBBEAN POETICS IN PEDRO PIETRI'S "PUERTO RICAN OBITUARY" AND KAMAU BRATHWAITE'S "ISLANDS AND EXILES"
par: Li Yun Alvarado
Publié: (2010)
par: Li Yun Alvarado
Publié: (2010)
Literary Lectures Presented at the Library of Congress.
Publié: (1973)
Publié: (1973)
Social network analysis, habitus and the field of literary activity
par: Li Li, et autres
Publié: (2024)
par: Li Li, et autres
Publié: (2024)
Madres, el portento quebrantando las sombras: la maternidad en la producción cultural hispánica
par: Souto Larios, Luz Celestina, et autres
Publié: (2025)
par: Souto Larios, Luz Celestina, et autres
Publié: (2025)
Three Perspectives on: Children's Classics in a Non-Classical Age
par: Fadiman, Clifton
Publié: (1972)
par: Fadiman, Clifton
Publié: (1972)
Beyond the Surface: Problems and Challenges in Young Adult Biographies.
par: Moore, Ann W.
Publié: (1990)
par: Moore, Ann W.
Publié: (1990)
Scales of Captivity
par: Brady, Mary Pat
Publié: (2022)
par: Brady, Mary Pat
Publié: (2022)
Plutarch's Science of Natural Problems
par: Meeusen, Michiel
Publié: (2020)
par: Meeusen, Michiel
Publié: (2020)
Corporate Financial Performance Following the Opening of China's High‐Speed Rail: A Firm‐Level Perspective on Supply Chain Performance
par: Fei Xu, et autres
Publié: (2024)
par: Fei Xu, et autres
Publié: (2024)
Think Only When You Need with Large Hybrid-Reasoning Models
par: Jiang, Lingjie, et autres
Publié: (2025)
par: Jiang, Lingjie, et autres
Publié: (2025)
Two‐Sided Effect of Preferential Rules of Origin on Export Resilience of Firms
par: Xue Zhenxiang, et autres
Publié: (2025)
par: Xue Zhenxiang, et autres
Publié: (2025)
CLA Booklist, Current Trends in Literature. Part 5
par: Theall, Bernard
Publié: (1971)
par: Theall, Bernard
Publié: (1971)
Samuel Langhorne Clemens: A Centennial for Tom Sawyer; An Annotated, Selected Bibliography.
par: Haviland, Virginia, Comp., et autres
Publié: (1976)
par: Haviland, Virginia, Comp., et autres
Publié: (1976)
The Challenge of Bewilderment
par: Armstrong, Paul B.
Publié: (2023)
par: Armstrong, Paul B.
Publié: (2023)
To Each Generation Its Own Rabbits
par: Flanagan, Dennis
Publié: (1974)
par: Flanagan, Dennis
Publié: (1974)
French Children's Classics: Tradition in a Non-Traditional Age
par: Jan, Isabelle
Publié: (1972)
par: Jan, Isabelle
Publié: (1972)
What Makes a Book Survive? Or, "Wild Tales Which Made the Child A Man"
par: Alderson, Brian
Publié: (1972)
par: Alderson, Brian
Publié: (1972)
Change and Challenge in the Literature Curriculum.
par: Ediger, Marlow
Publié: (2002)
par: Ediger, Marlow
Publié: (2002)
Children's Books: Current Trends.
par: Nist, Joan Stidham
Publié: (1980)
par: Nist, Joan Stidham
Publié: (1980)
The Best in Children's Books: The University of Chicago Guide to Children's Literature 1966-1972.
par: Sutherland, Zena, Ed.
Publié: (1973)
par: Sutherland, Zena, Ed.
Publié: (1973)
American Children's Classics: Which Will Fade, Which Endure?
par: Fenwick, Sara Innis
Publié: (1972)
par: Fenwick, Sara Innis
Publié: (1972)
Here Today--and Tomorrow?
par: Karl, Jean E.
Publié: (1987)
par: Karl, Jean E.
Publié: (1987)
Children's Literature: Books for Teaching It
par: Weber, Rosemary
Publié: (1970)
par: Weber, Rosemary
Publié: (1970)
Childhood in the Middle Ages and the Renaissance
par: Classen, Albrecht
Publié: (2017)
par: Classen, Albrecht
Publié: (2017)
Ho Ho Ho Hum: Christmas Books '74
par: Pollack, Pamela D.
Publié: (1974)
par: Pollack, Pamela D.
Publié: (1974)
Building Collections. Fantasy
par: Krapp, JoAnn Vergona
Publié: (2005)
par: Krapp, JoAnn Vergona
Publié: (2005)
SLJ Meets Lloyd Alexander
Publié: (1971)
Publié: (1971)
The Development of the International Standard Bibliographic Descriptions (ISBD) and Some Problems for Non-Roman Scripts
par: Kerr, Rosamond, et autres
Publié: (1977)
par: Kerr, Rosamond, et autres
Publié: (1977)
Chapter 16 Same-gender friendships and enmity in the Life of Eupraxia
par: Constantinou, Stavroula
Publié: (2021)
par: Constantinou, Stavroula
Publié: (2021)
After the Text
Publié: (2021)
Publié: (2021)
Documents similaires
-
Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models
par: Li, Zongqian, et autres
Publié: (2026) -
A Survey on Prompt Tuning
par: Li, Zongqian, et autres
Publié: (2025) -
PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning
par: Li, Zongqian, et autres
Publié: (2025) -
500xCompressor: Generalized Prompt Compression for Large Language Models
par: Li, Zongqian, et autres
Publié: (2024) -
MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark
par: Zhao, Qihao, et autres
Publié: (2024)