EnvOpt: new research shows optimizing agent environments cuts cost and boosts performance
AlexGDimakis · x · 2026-11-14
Alex Dimakis (UCSD) and collaborators introduce Environment Optimization (EnvOpt), new research led by @itea1001 with Huanzhi Mao, Qiuyang Mang, and Prof. Joey.
Key idea: an agent's cost and performance depend on three factors — 1) the model, 2) the harness, and 3) the environment structure. While most prior work optimizes the first two, EnvOpt studies how the environment presents information to the agent (e.g., how a company's Slack workspace, documents, and databases are organized) and how that affects performance and cost.
More from coding & agent
- Free metroidvania level generator turns a seed into a full tiled world — majidmanzarpour · 2026-11-14
- Open-source Agent Skill wraps DeepSeek API for docs, OCR and TTS — vista8 · 2026-11-14
- Fable-style scene rebuilt in pure three.js code, zero assets used — vinis_artstreaks · 2026-11-14
- 5 prompts this developer uses daily with Claude to get better coding results — jarrodwatts · 2026-11-14
- AI-designed main menu concept art for 'The Rat: Director's Cut' — chrisfirst · 2026-11-14
- agent-browser v0.43 cuts install size to 17MB and startup to 2ms — cramforce · 2026-11-14