{"total":17,"rows":[{"id":"2604.25727","title":"Toward Scalable Terminal Task Synthesis via Skill Graphs","created":"2026-04-28","cited_by_count":22,"area":null},{"id":"2608.05466","title":"Recursive Synthesis for Long-Horizon Terminal Tasks","created":"2026-08-05","cited_by_count":19,"area":null},{"id":"2605.22535","title":"TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks","created":"2026-05-21","cited_by_count":10,"area":null},{"id":"2606.03461","title":"What Makes Interaction Trajectories Effective for Training Terminal Agents?","created":"2026-06-02","cited_by_count":9,"area":null},{"id":"2608.18580","title":"FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis","created":"2026-08-19","cited_by_count":9,"area":null},{"id":"2605.29559","title":"LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents","created":"2026-05-28","cited_by_count":8,"area":null},{"id":"2608.06352","title":"CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks","created":"2026-08-06","cited_by_count":8,"area":null},{"id":"2609.04148","title":"Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments","created":"2026-09-03","cited_by_count":8,"area":null},{"id":"2608.27370","title":"Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2610.02710","title":"Self-Supervised Scaling of Terminal Environments for Scientific Domains","created":"2026-10-02","cited_by_count":1,"area":null},{"id":"2605.29115","title":"unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.07527","title":"Post-training is (Massive) Supervised Learning","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2609.20715","title":"Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.27717","title":"SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.04906","title":"Scaling Verifiable Environments for Long-horizon Work Agents","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05831","title":"Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.18484","title":"ReTerm: Recovery Training for Self-Improving Terminal Agents","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}