Cover Image

CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Mingzhi, Merler, Michele, Pavuluri, Raju, Patterson, Stacy
Format:	Preprint
Published:	2026
Subjects:	Software Engineering Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multi-task Code LLMs: Data Mix or Model Merge?
by: Zhu, Mingzhi, et al.
Published: (2026)

Granite Code Models: A Family of Open Foundation Models for Code Intelligence
by: Mishra, Mayank, et al.
Published: (2024)

Mitigating Gender Bias in Code Large Language Models via Model Editing
by: Qin, Zhanyue, et al.
Published: (2024)

Pull Requests as a Training Signal for Repo-Level Code Editing
by: Zhu, Qinglin, et al.
Published: (2026)

Training Versatile Coding Agents in Synthetic Environments
by: Zhu, Yiqi, et al.
Published: (2025)

MOSS: Enabling Code-Driven Evolution and Context Management for AI Agents
by: Zhu, Ming, et al.
Published: (2024)

Usage, Effects and Requirements for AI Coding Assistants in the Enterprise: An Empirical Study
by: Vukovic, Maja, et al.
Published: (2026)

RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation
by: Wang, Yanli, et al.
Published: (2024)

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

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

CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents
by: Sutawika, Lintang, et al.
Published: (2026)

CodeMind: Evaluating Large Language Models for Code Reasoning
by: Liu, Changshu, et al.
Published: (2024)

Effective Harness Engineering for Algorithm Discovery with Coding Agents
by: Ishibashi, Yoichi, et al.
Published: (2026)

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

SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning
by: Ding, Yangruibo, et al.
Published: (2024)

Can Coding Agents Reproduce Findings in Computational Materials Science?
by: Huang, Ziyang, et al.
Published: (2026)

OmniCode: A Benchmark for Evaluating Software Engineering Agents
by: Sonwane, Atharv, et al.
Published: (2026)

Asymmetric Goal Drift in Coding Agents Under Value Conflict
by: Saebo, Magnus, et al.
Published: (2026)

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

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

A Case Study of Web App Coding with OpenAI Reasoning Models
by: Cui, Yi
Published: (2024)

SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents
by: Zhao, Bingchen, et al.
Published: (2026)

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
by: Zhuo, Terry Yue, et al.
Published: (2025)

CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment
by: Jiang, Xue, et al.
Published: (2025)

Code Broker: A Multi-Agent System for Automated Code Quality Assessment
by: Attrah, Samer
Published: (2026)

Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination
by: Chen, Simin, et al.
Published: (2025)

CodeEditorBench: Evaluating Code Editing Capability of Large Language Models
by: Guo, Jiawei, et al.
Published: (2024)

SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades
by: Lam, Man Ho, et al.
Published: (2026)

CR-Bench: Evaluating the Real-World Utility of AI Code Review Agents
by: Pereira, Kristen, et al.
Published: (2026)

CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases
by: Liu, Xiangyan, et al.
Published: (2024)

Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs
by: Yang, Dayu, et al.
Published: (2025)

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

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

Risk Assessment Framework for Code LLMs via Leveraging Internal States
by: Huang, Yuheng, et al.
Published: (2025)

Enhancing Code Generation via Bidirectional Comment-Level Mutual Grounding
by: Di, Yifeng, et al.
Published: (2025)

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

CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
by: Yan, Weixiang, et al.
Published: (2023)

VisCoder2: Building Multi-Language Visualization Coding Agents
by: Ni, Yuansheng, et al.
Published: (2025)

Structure-aware Fine-tuning for Code Pre-trained Models
by: Wu, Jiayi, et al.
Published: (2024)

ReCode: Reinforcing Code Generation with Reasoning-Process Rewards
by: Fan, Lishui, et al.
Published: (2025)