Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

arXiv:2609.04148 · cs.AI, cs.CL · Submitted 2026-09-03 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-09-03

Updated: 2026-09-03

Code: https://github.com/harbor-framework/terminal-bench-2

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verifier — 56× in this paper · explained in 2 episodes
• Verification — 14× in this paper · explained in 2 episodes
• Ablation — 12× in this paper · explained in 1 episode
• Trace — 12× in this paper · explained in 2 episodes
• Benchmark — 10× in this paper · explained in 2 episodes
• Core — 10× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• Agent Skills — 2× in this paper · explained in 1 episode
• Aggregation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Active Regression — 1× in this paper · explained in 1 episode
• Decode — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Verifiability — 1× in this paper · explained in 2 episodes

Sources

• SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
• Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
• Toward Scalable Terminal Task Synthesis via Skill Graphs
• Endless Terminals: Scaling RL Environments for Terminal Agents
• SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks
• CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
• Tmax: A simple recipe for terminal agents
• R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
• RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms
• Recursive Synthesis for Long-Horizon Terminal Tasks
• CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion
• CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks
• Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
• Meta-Task: Turning Terminal Task Synthesis into a Terminal Task for Scalable Agent Training
• LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
• ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders
• On Data Engineering for Scaling LLM Terminal Capabilities
• OpenThoughts-Agent: Data Recipes for Agentic Models
• SETA: Scaling Environments for Terminal Agents

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