The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs
Paper • 2506.18403 • Published • 3
Code
-
-
ReCode: Updating Code API Knowledge with Reinforcement Learning
Paper • 2506.20495 • Published • 10 -
SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution
Paper • 2507.23348 • Published • 12 -
LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering
Paper • 2509.09614 • Published • 7 -
LongCodeZip: Compress Long Context for Code Language Models
Paper • 2510.00446 • Published • 108 -
CoDA: Coding LM via Diffusion Adaptation
Paper • 2510.03270 • Published • 43 -
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
Paper • 2510.08697 • Published • 40 -
A Survey of Vibe Coding with Large Language Models
Paper • 2510.12399 • Published • 50 -
ReCode: Unify Plan and Action for Universal Granularity Control
Paper • 2510.23564 • Published • 123 -
VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation
Paper • 2511.02778 • Published • 104 -
WebVIA: A Web-based Vision-Language Agentic Framework for Interactive and Verifiable UI-to-Code Generation
Paper • 2511.06251 • Published • 14 -
Agentic Rubrics as Contextual Verifiers for SWE Agents
Paper • 2601.04171 • Published • 13 -
MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences
Paper • 2601.06789 • Published • 82 -
ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development
Paper • 2601.11077 • Published • 67 -
Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model
Paper • 2601.15892 • Published • 55 -
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Paper • 2601.11868 • Published • 37 -
CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
Paper • 2602.01785 • Published • 97 -
SWE-Universe: Scale Real-World Verifiable Environments to Millions
Paper • 2602.02361 • Published • 61 -
Code2World: A GUI World Model via Renderable Code Generation
Paper • 2602.09856 • Published • 201 -
K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model
Paper • 2602.19128 • Published • 7 -
Agentic Code Reasoning
Paper • 2603.01896 • Published • 10 -
SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale
Paper • 2602.23866 • Published • 91 -
Qwen3-Coder-Next Technical Report
Paper • 2603.00729 • Published • 65 -
Towards a Neural Debugger for Python
Paper • 2603.09951 • Published • 7 -
CodePercept: Code-Grounded Visual STEM Perception for MLLMs
Paper • 2603.10757 • Published • 15 -
InCoder-32B: Code Foundation Model for Industrial Scenarios
Paper • 2603.16790 • Published • 312 -
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
Paper • 2604.04707 • Published • 204 -
Self-Execution Simulation Improves Coding Models
Paper • 2604.03253 • Published • 35 -
Automating Database-Native Function Code Synthesis with LLMs
Paper • 2604.06231 • Published • 17 -
CodeTracer: Towards Traceable Agent States
Paper • 2604.11641 • Published • 38 -
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
Paper • 2604.14228 • Published • 25 -
OpenGame: Open Agentic Coding for Games
Paper • 2604.18394 • Published • 84 -
WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models
Paper • 2604.18224 • Published • 22 -
PlayCoder: Making LLM-Generated GUI Code Playable
Paper • 2604.19742 • Published • 26 -
A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
Paper • 2604.19572 • Published • 23 -
Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows
Paper • 2604.28139 • Published • 42 -
ClawGym: A Scalable Framework for Building Effective Claw Agents
Paper • 2604.26904 • Published • 54 -
Teaching Language Models to Think in Code
Paper • 2605.07237 • Published • 31 -
Orchard: An Open-Source Agentic Modeling Framework
Paper • 2605.15040 • Published • 21 -
Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution
Paper • 2605.15301 • Published • 22 -
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
Paper • 2605.18401 • Published • 130 -
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
Paper • 2605.14678 • Published • 108 -
ETCHR: Editing To Clarify and Harness Reasoning
Paper • 2605.23897 • Published • 13 -
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
Paper • 2605.27366 • Published • 29 -
GenClaw: Code-Driven Agentic Image Generation
Paper • 2605.30248 • Published • 40 -
LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
Paper • 2605.29559 • Published • 17 -
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
Paper • 2606.06492 • Published • 92 -
When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents
Paper • 2606.05806 • Published • 23 -
SWE-Explore: Benchmarking How Coding Agents Explore Repositories
Paper • 2606.07297 • Published • 119 -
DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch
Paper • 2606.10728 • Published • 34 -
Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields
Paper • 2606.11042 • Published • 21 -
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
Paper • 2606.12344 • Published • 68 -
LLM Agents Can See Code Repositories
Paper • 2606.14061 • Published • 20 -
CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?
Paper • 2606.15300 • Published • 13 -
FastContext: Training Efficient Repository Explorer for Coding Agents
Paper • 2606.14066 • Published • 91 -
Guava: An Effective and Universal Harness for Embodied Manipulation
Paper • 2606.18363 • Published • 28 -
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
Paper • 2606.22883 • Published • 33 -
Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence
Paper • 2606.15932 • Published • 31 -
The Verification Horizon: No Silver Bullet for Coding Agent Rewards
Paper • 2606.26300 • Published • 30