Qwen Paper Proposes Elastic Horizon, a Closed-Loop Controller for Agentic RL Interaction Budgets
dair_ai · x · 2026-09-11
A Qwen team paper tackles interaction horizon scheduling in agentic RL: scaling per-episode environment interactions helps long-horizon agents, but existing curricula are open-loop and monotonic.
The authors define the "effective interaction frontier" — beyond it, extra interactions yield diminishing returns while costs grow linearly, with clear saturation plateaus on AppWorld and BFCL. Elastic Horizon is a closed-loop controller that tracks this boundary using the 90th percentile of successful trajectory lengths, a statistic already available during training.
More from coding & agent
- AWS on agent prompt caching: explicit + implicit patterns to slash token costs — AWS ML Blog · 2026-10-27
- He gave his AI agent a phone number and email — then hired it as social media manager — heyshrutimishra · 2026-10-27
- Firecrawl launches Alexandria company-data API and announces $75M Series B — devdigest · 2026-10-27
- Entire Builds a Git Forge Designed for Agent-Human Collaboration — lizziepika · 2026-10-27
- 'Let an agent run wild on vague goals and it makes your code worse 9 out of 10 times' — eptwts · 2026-10-27
- LangChain to demo the in-house design agent its team uses daily, this Wednesday — LangChain · 2026-10-27