Imagen de Portada

Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Kovács, Ádám
Formato:	Preprint
Publicado:	2026
Materias:	Software Engineering Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
por: Phan, Huy Nhat, et al.
Publicado: (2024)

GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging
por: Ni, Ziyi, et al.
Publicado: (2025)

Beyond Isolated Tasks: A Framework for Evaluating Coding Agents on Sequential Software Evolution
por: Shastry, KN Ajay, et al.
Publicado: (2026)

Beyond Output Correctness: Benchmarking and Evaluating Large Language Model Reasoning in Coding Tasks
por: Li, Yuangang, et al.
Publicado: (2026)

Output Format Biases in the Evaluation of Large Language Models for Code Translation
por: Macedo, Marcos, et al.
Publicado: (2024)

ToolFuzz -- Automated Agent Tool Testing
por: Milev, Ivan, et al.
Publicado: (2025)

Architecture Without Architects: How AI Coding Agents Shape Software Architecture
por: Konrad, Phongsakon Mark, et al.
Publicado: (2026)

User Centric Evaluation of Code Generation Tools
por: Miah, Tanha, et al.
Publicado: (2024)

RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution
por: Liu, Aofan, et al.
Publicado: (2025)

CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMs
por: Basha, Manaal, et al.
Publicado: (2025)

Less is More: Towards Green Code Large Language Models via Unified Structural Pruning
por: Yang, Guang, et al.
Publicado: (2024)

RedCode: Risky Code Execution and Generation Benchmark for Code Agents
por: Guo, Chengquan, et al.
Publicado: (2024)

ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents
por: Li, Dawei, et al.
Publicado: (2026)

TaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models
por: Tambon, Florian, et al.
Publicado: (2024)

EfficientUICoder: Efficient MLLM-based UI Code Generation via Input and Output Token Compression
por: Xiao, Jingyu, et al.
Publicado: (2025)

CodeGenLink: A Tool to Find the Likely Origin and License of Automatically Generated Code
por: Bifolco, Daniele, et al.
Publicado: (2025)

Code Review Agent Benchmark
por: Zhang, Yuntong, et al.
Publicado: (2026)

Applying an Agentic Coding Tool for Improving Published Algorithm Implementations
por: Suwannik, Worasait
Publicado: (2026)

GeoCode-GPT: A Large Language Model for Geospatial Code Generation Tasks
por: Hou, Shuyang, et al.
Publicado: (2024)

CodeR: Issue Resolving with Multi-Agent and Task Graphs
por: Chen, Dong, et al.
Publicado: (2024)

DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
por: Chen, Aili, et al.
Publicado: (2026)

Runtime-Structured Task Decomposition for Agentic Coding Systems
por: Asthana, Shubhi, et al.
Publicado: (2026)

Task Abstention for Large Language Models in Code Generation
por: Zhou, Yanke, et al.
Publicado: (2026)

Ambiguity Resolution with Human Feedback for Code Writing Tasks
por: Nandan, Aditey, et al.
Publicado: (2025)

An Empirical Study of Knowledge Distillation for Code Understanding Tasks
por: Wang, Ruiqi, et al.
Publicado: (2025)

Automated Benchmark Generation for Repository-Level Coding Tasks
por: Vergopoulos, Konstantinos, et al.
Publicado: (2025)

Workflows vs Agents for Code Translation
por: Gray, Henry, et al.
Publicado: (2025)

Theory of Code Space: Do Code Agents Understand Software Architecture?
por: Sapunov, Grigory
Publicado: (2026)

SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion
por: Ma, George, et al.
Publicado: (2025)

Code for Machines, Not Just Humans: Quantifying AI-Friendliness with Code Health Metrics
por: Borg, Markus, et al.
Publicado: (2026)

Analyzing Message-Code Inconsistency in AI Coding Agent-Authored Pull Requests
por: Gong, Jingzhi, et al.
Publicado: (2026)

Code Researcher: Deep Research Agent for Large Systems Code and Commit History
por: Singh, Ramneet, et al.
Publicado: (2025)

ASA: Training-Free Representation Engineering for Tool-Calling Agents
por: Wang, Youjin, et al.
Publicado: (2026)

MCP-Zero: Active Tool Discovery for Autonomous LLM Agents
por: Fei, Xiang, et al.
Publicado: (2025)

Schema First Tool APIs for LLM Agents: A Controlled Study of Tool Misuse, Recovery, and Budgeted Performance
por: Sigdel, Akshey, et al.
Publicado: (2026)

Scaling Coding Agents via Atomic Skills
por: Ma, Yingwei, et al.
Publicado: (2026)

SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
por: Orlanski, Gabriel, et al.
Publicado: (2026)

DialogAgent: An Auto-engagement Agent for Code Question Answering Data Production
por: Liang, Xiaoyun, et al.
Publicado: (2024)

Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code
por: Kim, Myeongsoo, et al.
Publicado: (2026)

Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study
por: Trivedi, Priyansh, et al.
Publicado: (2026)