Terminal-World: Large-Scale Environment Synthesis for Terminal Agents

The paper presents Terminal-World, an automated pipeline that uses Agent Skills to generate diverse terminal‑agent training data, builds over 5,700 environments, and trains models that outperform existing baselines on multiple benchmarks despite using far less data.

Agent SkillsTerminal-Worldbenchmark

0 likes · 4 min read

Terminal-World: Large-Scale Environment Synthesis for Terminal Agents

Machine Heart

May 7, 2026 · Artificial Intelligence

How TACO Lets CLI Agents Self‑Evolve to Drop Useless Context

TACO is a plug‑and‑play, training‑free framework that lets terminal‑based autonomous agents automatically learn compression rules to filter low‑value output while preserving critical decision cues, achieving higher task success rates and better token efficiency across multiple terminal‑related benchmarks.

Context CompressionLLMSelf‑Evolving Rules

0 likes · 14 min read

How TACO Lets CLI Agents Self‑Evolve to Drop Useless Context

PaperAgent

May 3, 2026 · Artificial Intelligence

Skill Graphs Reveal Why Training Diversity Beats Quantity for Terminal Agents

The paper shows that, instead of increasing the number of training tasks, controlling the diversity of scene‑skill combinations via a large‑scale Skill Graph dramatically improves terminal‑agent performance, with Qwen3‑32B surpassing a 480B model on the Terminal‑Bench 2.0 benchmark.

LLMQwen3Skill Graphs

0 likes · 9 min read

Skill Graphs Reveal Why Training Diversity Beats Quantity for Terminal Agents