Unverified50% confidenceBenchmarkExact time
On the four-box Sokoban task, an action-only planner solved only 2%, far below Agima's 40%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
Related Entities
Related Claims
UnverifiedIn tasks requiring more than 5 steps, the success rate of the strongest models drops sharply from over 80% at the first step to 40% or even lower at subsequent steps, exhibiting an exponential decline.62% similarUnverified即便是GPT-4级别的Agent，面对含有5步以上工具调用的复杂任务时，端到端成功率往往低于60%62% similarUnverifiedCompared with the approach of "fine-tuning every sub-step", AdaRSI achieved a slightly higher success rate while consuming only 28% of the GPU time and 22% of the self-collected demonstration data.61% similarUnverifiedOn ARC-AGI 3, Astra completed 96% of levels at the highest setting using fewer steps than the human baseline, reducing actions by approximately 50% on average.60% similarUnverified简单任务用小模型完成的成本可能只有大模型的十分之一甚至更低59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1073378API
curl https://kongchang.com/api/v1/knowledge/claims/1073378MCP
get_claim(id=1073378)