Copertina

ARIADNE: Agentic Reward-Informed Adaptive Decision Exploration via Blackboard-Driven MCTS for Competitive Program Generation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wei, Minnan, Chen, Xiang, Niu, Xiaoshuai, Chen, Siyu
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Evaluating and Improving Large Language Models for Competitive Program Generation
di: Wei, Minnan, et al.
Pubblicazione: (2025)

Improving vulnerability type prediction and line-level detection via adversarial training-based data augmentation and multi-task learning
di: Chen, Siyu, et al.
Pubblicazione: (2025)

A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement
di: Zhang, Huan, et al.
Pubblicazione: (2024)

AdverMCTS: Combating Pseudo-Correctness in Code Generation via Adversarial Monte Carlo Tree Search
di: Li, Qingyao, et al.
Pubblicazione: (2026)

SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflows
di: Zhou, Jingwen, et al.
Pubblicazione: (2025)

Uncovering Business Logic Bugs via Semantics-Driven Unit Test Generation
di: Yang, Chen, et al.
Pubblicazione: (2026)

TestForge: Feedback-Driven, Agentic Test Suite Generation
di: Jain, Kush, et al.
Pubblicazione: (2025)

RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation
di: Li, Qingyao, et al.
Pubblicazione: (2024)

MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution
di: Wang, Yibo, et al.
Pubblicazione: (2025)

Lemma Discovery in Agentic Program Verification
di: Zhao, Huan, et al.
Pubblicazione: (2026)

May the Feedback Be with You! Unlocking the Power of Feedback-Driven Deep Learning Framework Fuzzing via LLMs
di: Yang, Shaoyu, et al.
Pubblicazione: (2025)

MASFuzzer: Fuzz Driver Generation and Adaptive Scheduling via Multidimensional API Sequences
di: Liu, Xingyu, et al.
Pubblicazione: (2026)

Interleaved Learning and Exploration: A Self-Adaptive Fuzz Testing Framework for MLIR
di: Sun, Zeyu, et al.
Pubblicazione: (2025)

An Empirical Study on Commit Message Generation using LLMs via In-Context Learning
di: Wu, Yifan, et al.
Pubblicazione: (2025)

RAG-Reflect: Agentic Retrieval-Augmented Generation with Reflections for Comment-Driven Code Maintenance on Stack Overflow
di: Shanto, Mehedi Hasan, et al.
Pubblicazione: (2026)

EviACT: An Evidence-to-Action Framework for Agentic Program Repair
di: Meng, Qianru, et al.
Pubblicazione: (2026)

DePro: Understanding the Role of LLMs in Debugging Competitive Programming Code
di: Parvez, Nabiha, et al.
Pubblicazione: (2026)

AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities
di: Wang, Huanting, et al.
Pubblicazione: (2025)

Automatic Smart Contract Comment Generation via Large Language Models and In-Context Learning
di: Zhao, Junjie, et al.
Pubblicazione: (2023)

CodeContests+: High-Quality Test Case Generation for Competitive Programming
di: Wang, Zihan, et al.
Pubblicazione: (2025)

BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
di: Li, Yuanhao, et al.
Pubblicazione: (2026)

Enhancing LLM-based Specification Generation via Program Slicing and Logical Deletion
di: Chen, Zehan, et al.
Pubblicazione: (2025)

HerAgent: Rethinking the Automated Environment Deployment via Hierarchical Test Pyramid
di: Li, Xiang, et al.
Pubblicazione: (2026)

SpaceTime Programming: Live and Omniscient Exploration of Code and Execution
di: Döderlein, Jean-Baptiste, et al.
Pubblicazione: (2026)

Testing Question Answering Software with Context-Driven Question Generation
di: Liu, Shuang, et al.
Pubblicazione: (2025)

SeqTG: Scalable Combinatorial Test Generation via Sequential Integer Linear Programming
di: Yang, Sitong, et al.
Pubblicazione: (2026)

Curiosity-Driven Testing for Sequential Decision-Making Process
di: He, Junda, et al.
Pubblicazione: (2025)

No Man is an Island: Towards Fully Automatic Programming by Code Search, Code Generation and Program Repair
di: Zhang, Quanjun, et al.
Pubblicazione: (2024)

RepoZero: Can LLMs Generate a Code Repository from Scratch?
di: Zhang, Zhaoxi, et al.
Pubblicazione: (2026)

POLARIS: Is Multi-Agentic Reasoning the Next Wave in Engineering Self-Adaptive Systems?
di: Pandey, Divyansh, et al.
Pubblicazione: (2025)

Agentic Services Computing
di: Deng, Shuiguang, et al.
Pubblicazione: (2025)

An Iterative Test-and-Repair Framework for Competitive Code Generation
di: Tang, Lingxiao, et al.
Pubblicazione: (2026)

Informed and Assessable Observability Design Decisions in Cloud-native Microservice Applications
di: Borges, Maria C., et al.
Pubblicazione: (2024)

Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair
di: Cheng, Runxiang, et al.
Pubblicazione: (2026)

Agentic Bug Reproduction for Effective Automated Program Repair at Google
di: Cheng, Runxiang, et al.
Pubblicazione: (2025)

AetherCode: Evaluating LLMs' Ability to Win In Premier Programming Competitions
di: Wang, Zihan, et al.
Pubblicazione: (2025)

LogiCase: Effective Test Case Generation from Logical Description in Competitive Programming
di: Sung, Sicheol, et al.
Pubblicazione: (2025)

Towards Causal Analysis of Empirical Software Engineering Data: The Impact of Programming Languages on Coding Competitions
di: Furia, Carlo A., et al.
Pubblicazione: (2023)

M2QCode: A Model-Driven Framework for Generating Multi-Platform Quantum Programs
di: Guo, Xiaoyu, et al.
Pubblicazione: (2025)

Tumbling Down the Rabbit Hole: How do Assisting Exploration Strategies Facilitate Grey-box Fuzzing?
di: Wu, Mingyuan, et al.
Pubblicazione: (2024)