Self-Supervised Scaling of Terminal Environments for Scientific Domains
cs.SE, cs.AI
Submitted: 2026-10-02
Updated: 2026-10-02
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- DeepCoder: Learning to Write Programs
- Metamorphic Testing: A New Approach for Generating Next Test Cases
- World Models
- Measuring Coding Challenge Competence With APPS
- Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding
- Tmax: A simple recipe for terminal agents
- Large Language Model Agent: A Survey on Methodology, Applications and Challenges
- Training Software Engineering Agents and Verifiers with SWE-Gym
- LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
- On Data Engineering for Scaling LLM Terminal Capabilities
- OpenThoughts-Agent: Data Recipes for Agentic Models
- Neural Programmer-Interpreters
- SETA: Scaling Environments for Terminal Agents
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- ReAct: Synergizing Reasoning and Acting in Language Models
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties