Long-horizon agentic task on DeepSearchQA
66PerformanceAggAgent
Evaluation Results
| Method | Links | |
|---|---|---|
| AggAgentBackbone=Qwen3.5-122B, Aggregation Category=LLM-based Aggregation, Number of Rollouts (K)=82026.04 | 66 | |
| AggAgentBackbone=MiniMax-M2.5, Aggregation Category=LLM-based Aggregation, Number of Rollouts (K)=82026.04 | 65.33 | |
| Summary AggregationBackbone=Qwen3.5-122B, Aggregation Category=LLM-based Aggregation, Number of Rollouts (K)=82026.04 | 64 | |
| Best-of-NBackbone=MiniMax-M2.5, Aggregation Category=Heuristic Aggregation, Number of Rollouts (K)=82026.04 | 64 | |
| Solution AggregationBackbone=Qwen3.5-122B, Aggregation Category=LLM-based Aggregation, Number of Rollouts (K)=82026.04 | 62.67 | |
| Solution AggregationBackbone=MiniMax-M2.5, Aggregation Category=LLM-based Aggregation, Number of Rollouts (K)=82026.04 | 62 | |
| Summary AggregationBackbone=MiniMax-M2.5, Aggregation Category=LLM-based Aggregation, Number of Rollouts (K)=82026.04 | 61.33 | |
| Best-of-NBackbone=Qwen3.5-122B, Aggregation Category=Heuristic Aggregation, Number of Rollouts (K)=82026.04 | 57.33 | |
| Fewest Tool CallsBackbone=MiniMax-M2.5, Aggregation Category=Heuristic Aggregation, Number of Rollouts (K)=82026.04 | 56 | |
| Fewest Tool CallsBackbone=Qwen3.5-122B, Aggregation Category=Heuristic Aggregation, Number of Rollouts (K)=82026.04 | 54.67 | |
| Pass@1Backbone=MiniMax-M2.5, Aggregation Category=Single Rollout, Number of Rollouts (K)=12026.04 | 54.42 | |
| AggAgentBackbone=GLM-4.7-Flash, Aggregation Category=LLM-based Aggregation, Number of Rollouts (K)=82026.04 | 49.33 | |
| Pass@1Backbone=Qwen3.5-122B, Aggregation Category=Single Rollout, Number of Rollouts (K)=12026.04 | 49.25 | |
| Summary AggregationBackbone=GLM-4.7-Flash, Aggregation Category=LLM-based Aggregation, Number of Rollouts (K)=82026.04 | 47.33 | |
| Solution AggregationBackbone=GLM-4.7-Flash, Aggregation Category=LLM-based Aggregation, Number of Rollouts (K)=82026.04 | 46 | |
| Best-of-NBackbone=GLM-4.7-Flash, Aggregation Category=Heuristic Aggregation, Number of Rollouts (K)=82026.04 | 35.33 | |
| Fewest Tool CallsBackbone=GLM-4.7-Flash, Aggregation Category=Heuristic Aggregation, Number of Rollouts (K)=82026.04 | 33.33 | |
| Pass@1Backbone=GLM-4.7-Flash, Aggregation Category=Single Rollout, Number of Rollouts (K)=12026.04 | 32.42 |