CodeSkill: Latent Skill Abstraction for Long-Horizon Code Agents
cs.AI
Submitted: 2026-09-27
Updated: 2026-09-27
Code: https://github.com/laude-institute/terminal-bench
Terminology
Sources
- gpt-oss-120b & gpt-oss-20b Model Card
- EvoSkill: Automated Skill Discovery for Multi-Agent Systems
- Program Synthesis with Large Language Models
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- Qwen3-Coder-Next Technical Report
- Evaluating Large Language Models Trained on Code
- FullStack Bench: Evaluating LLMs as Full Stack Coders
- Group-in-Group Policy Optimization for LLM Agent Training
- CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
- Explainable Behavior Cloning: Teaching Large Language Model Agents through Learning by Demonstration
- KL-Regularized Reinforcement Learning is Designed to Mode Collapse
- Qwen2.5-Coder Technical Report
- RealBench: Benchmarking Verilog Generation Models with Real-World IP Designs
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- KernelBench: Can LLMs Write Efficient GPU Kernels?
- Seed-Coder: Let the Code Model Curate Data for Itself
- MedGemma Technical Report
- Kimi K2.5: Visual Agentic Intelligence
- Kimi K2: Open Agentic Intelligence
- SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection