Unverified50% confidenceBenchmarkExact time
The Mann-Whitney U test shows that task_score under the naive survival reward falls below the random-policy baseline, with p=0.012.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/7/2026
First Seen
Valid until: 12/6/2026
Sources
Related Entities
Related Claims
UnverifiedIn the experiment, the task_score under the shaped reward configuration was only 0.125, compared to 0.417 for the naive reward, with an effect size of d=4.47.73% similarUnverifiedOpenAI's chart shows that at lower test-time compute levels, the model's success rate on this problem is close to zero, with occasional success only under extremely long reasoning chains.68% similarUnverified斯坦福大学的AgentBench基准测试（2023年）量化证明，在复杂多步骤任务中纯ReAct范式的成功率往往不超过30%68% similarUnverified在MATH数据集的Level 5竞赛级难题上，前沿模型准确率仍低于60%65% similarVerifiedReAct's errors amplify in a chain: if the accuracy per step is p, the overall success rate after n steps is approximately p to the power of n; with a per-step accuracy of 95%, the overall success rate drops to approximately 59.9% after 10 steps and only 35.8% after 20 steps.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/870232API
curl https://kongchang.com/api/v1/knowledge/claims/870232MCP
get_claim(id=870232)