Imagen de Portada

Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ning, Jingjie, Li, Xueqi, Yu, Chengyu
Formato:	Preprint
Publicado:	2026
Materias:	Software Engineering Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Adaptable and Precise: Enterprise-Scenario LLM Function-Calling Capability Training Pipeline
por: Zeng, Guancheng, et al.
Publicado: (2024)

An Empirical Study on Failures in Automated Issue Solving
por: Liu, Simiao, et al.
Publicado: (2025)

CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging
por: Islam, Md. Ashraful, et al.
Publicado: (2025)

kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation
por: Siva, Rohan, et al.
Publicado: (2026)

How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code
por: Lee, Seonghyeon, et al.
Publicado: (2025)

GoNoGo: An Efficient LLM-based Multi-Agent System for Streamlining Automotive Software Release Decision-Making
por: Khoee, Arsham Gholamzadeh, et al.
Publicado: (2024)

RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance
por: Jin, Haolin, et al.
Publicado: (2024)

ChainStream: An LLM-based Framework for Unified Synthetic Sensing
por: Liu, Jiacheng, et al.
Publicado: (2024)

Your Simulation Runs but Solves the Wrong Physics: PDE-Grounded Intent Verification for LLM-Generated Multiphysics Simulation Code
por: Song, Zhenghan, et al.
Publicado: (2026)

Drift-Bench: Diagnosing Cooperative Breakdowns in LLM Agents under Input Faults via Multi-Turn Interaction
por: Bao, Han, et al.
Publicado: (2026)

SoAy: A Solution-based LLM API-using Methodology for Academic Information Seeking
por: Wang, Yuanchun, et al.
Publicado: (2024)

A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning
por: Li, Xinzhe
Publicado: (2024)

Crystal: Illuminating LLM Abilities on Language and Code
por: Tao, Tianhua, et al.
Publicado: (2024)

AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications
por: Shen, Leming, et al.
Publicado: (2025)

Issue Localization via LLM-Driven Iterative Code Graph Searching
por: Jiang, Zhonghao, et al.
Publicado: (2025)

Functional Programming Paradigm of Python for Scientific Computation Pipeline Integration
por: Zhang, Chen, et al.
Publicado: (2024)

Multi-agent Application System in Office Collaboration Scenarios
por: Sun, Songtao, et al.
Publicado: (2025)

MEMCoder: Multi-dimensional Evolving Memory for Private-Library-Oriented Code Generation
por: Li, Mofei, et al.
Publicado: (2026)

Verification Limits Code LLM Training
por: Gureja, Srishti, et al.
Publicado: (2025)

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
por: Luo, Jane, et al.
Publicado: (2025)

From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future
por: Jin, Haolin, et al.
Publicado: (2024)

Blueprint First, Model Second: A Framework for Deterministic LLM Workflow
por: Qiu, Libin, et al.
Publicado: (2025)

CodeS: Natural Language to Code Repository via Multi-Layer Sketch
por: Zan, Daoguang, et al.
Publicado: (2024)

Pragmatic Reasoning improves LLM Code Generation
por: Cao, Zhuchen, et al.
Publicado: (2025)

Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries
por: Zhang, Xing, et al.
Publicado: (2026)

NeuroSync: Intent-Aware Code-Based Problem Solving via Direct LLM Understanding Modification
por: Zhang, Wenshuo, et al.
Publicado: (2025)

WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning
por: Yu, Zhaojian, et al.
Publicado: (2023)

aiXcoder-7B: A Lightweight and Effective Large Language Model for Code Processing
por: Jiang, Siyuan, et al.
Publicado: (2024)

Co-Learning: Code Learning for Multi-Agent Reinforcement Collaborative Framework with Conversational Natural Language Interfaces
por: Yu, Jiapeng, et al.
Publicado: (2024)

Planning to Explore: Curiosity-Driven Planning for LLM Test Generation
por: Amayuelas, Alfonso, et al.
Publicado: (2026)

An evaluation of LLM code generation capabilities through graded exercises
por: Jiménez, Álvaro Barbero
Publicado: (2024)

LocAgent: Graph-Guided LLM Agents for Code Localization
por: Chen, Zhaoling, et al.
Publicado: (2025)

LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation
por: Zhang, Ziyao, et al.
Publicado: (2024)

Learning to Ask: When LLM Agents Meet Unclear Instruction
por: Wang, Wenxuan, et al.
Publicado: (2024)

EvoConfig: Self-Evolving Multi-Agent Systems for Efficient Autonomous Environment Configuration
por: Guo, Xinshuai, et al.
Publicado: (2026)

CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks
por: Jiang, Hongchao, et al.
Publicado: (2025)

WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models
por: Fan, Shengda, et al.
Publicado: (2024)

Automated Business Process Analysis: An LLM-Based Approach to Value Assessment
por: De Michele, William, et al.
Publicado: (2025)

An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks
por: Zhou, Xin, et al.
Publicado: (2025)

Collaboration is all you need: LLM Assisted Safe Code Translation
por: Karanjai, Rabimba, et al.
Publicado: (2025)