CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
cs.SE, cs.AI, cs.CL
Submitted: 2026-05-13
Updated: 2026-11-07
Code: https://github.com/rpi-nsl/CRANE
Terminology
Sources
- Qwen3-Coder-Next Technical Report
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- THINK-Bench: Evaluating Thinking Efficiency and Chain-of-Thought Quality of Large Reasoning Models
- Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- OpenHands: An Open Platform for AI Software Developers as Generalist Agents
- Qwen3 Technical Report
- AdaMerging: Adaptive Model Merging for Multi-Task Learning
- BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters