CLI-Universe synthesizes a verified 6K dataset of terminal-agent tasks that, when used to fine-tune Qwen3-32B, reaches 33.4% on Terminal-Bench 2.0 and sets a new open-source SOTA for models at or below 32B parameters.
Termigen: High-fidelity environment and robust trajectory synthesis for terminal agents
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
years
2026 10representative citing papers
Terminal-World is a skill-based synthesis pipeline that generates 5,723 training environments and produces Terminal-World-32B which outperforms baselines on Terminal-Bench 2.0 using only 1.2% of the data.
Qwen-AgentWorld are language world models that simulate multi-domain agent environments and boost general agent capabilities via decoupled RL simulation and unified foundation model training.
Tmax is an open RL training recipe for terminal agents that achieves 27% on Terminal-Bench 2.0 with a 9B model via a novel data generation taxonomy combining difficulty control, personas, and verifier diversification.
Trajectories from weaker agents outperform stronger ones for training terminal agents due to environment-grounded supervision that exposes inspect-act-verify behaviors.
LiteCoder-Terminal-Gen creates synthetic terminal datasets that, after SFT and DMPO on Qwen models, yield 29.06%, 18.54%, and 34.00% pass@1 on Terminal Bench 1.0, 2.0, and Pro.
Claw-Anything benchmark tests LLM agents on proactive assistance in complex simulated user digital environments with long histories, interdependent services, and noise, where GPT-5.5 scores 34.5% pass@1.
OpenComputer introduces a verifier-grounded framework with state verifiers, self-evolving layers, task synthesis, and auditable evaluation for 33 desktop apps and 1000 tasks to support computer-use AI agents.
SkillSynth uses a scenario-mediated skill graph to sample workflow paths and generate executable terminal tasks, enabling controlled diversity in training trajectories for agents.
Execution-grounded multi-turn OS trajectories from 4D intents and a role-locked simulator lift Qwen3-8B ClawEval pass@1 from 19.3 to 37.7, beating GPT-4o and Qwen3-32B zero-shot.
citing papers explorer
-
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
CLI-Universe synthesizes a verified 6K dataset of terminal-agent tasks that, when used to fine-tune Qwen3-32B, reaches 33.4% on Terminal-Bench 2.0 and sets a new open-source SOTA for models at or below 32B parameters.
-
Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
Terminal-World is a skill-based synthesis pipeline that generates 5,723 training environments and produces Terminal-World-32B which outperforms baselines on Terminal-Bench 2.0 using only 1.2% of the data.
-
Qwen-AgentWorld: Language World Models for General Agents
Qwen-AgentWorld are language world models that simulate multi-domain agent environments and boost general agent capabilities via decoupled RL simulation and unified foundation model training.
-
Tmax: A simple recipe for terminal agents
Tmax is an open RL training recipe for terminal agents that achieves 27% on Terminal-Bench 2.0 with a 9B model via a novel data generation taxonomy combining difficulty control, personas, and verifier diversification.
-
What Makes Interaction Trajectories Effective for Training Terminal Agents?
Trajectories from weaker agents outperform stronger ones for training terminal agents due to environment-grounded supervision that exposes inspect-act-verify behaviors.
-
LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
LiteCoder-Terminal-Gen creates synthetic terminal datasets that, after SFT and DMPO on Qwen models, yield 29.06%, 18.54%, and 34.00% pass@1 on Terminal Bench 1.0, 2.0, and Pro.
-
Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World
Claw-Anything benchmark tests LLM agents on proactive assistance in complex simulated user digital environments with long histories, interdependent services, and noise, where GPT-5.5 scores 34.5% pass@1.
-
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
OpenComputer introduces a verifier-grounded framework with state verifiers, self-evolving layers, task synthesis, and auditable evaluation for 33 desktop apps and 1000 tasks to support computer-use AI agents.
-
Toward Scalable Terminal Task Synthesis via Skill Graphs
SkillSynth uses a scenario-mediated skill graph to sample workflow paths and generate executable terminal tasks, enabling controlled diversity in training trajectories for agents.
-
ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories
Execution-grounded multi-turn OS trajectories from 4D intents and a role-locked simulator lift Qwen3-8B ClawEval pass@1 from 19.3 to 37.7, beating GPT-4o and Qwen3-32B zero-shot.