Parallel test-time scaling (TTS) has been shown to enhance reasoning in large language models by generating and aggregating multiple independent reasoning paths. Internal confidence scores can further improve this process by identifying paths of varying quality. However, existing methods remain computationally inefficient, as low-quality paths are fully expanded before being evaluated. In this work, we aim to improve the use of internal confidence signals for better model performance and computational efficiency. We begin by offering a new perspective on the role of confidence in aggregation, showing that it is most impactful for questions near the decision boundary. Notably, when amplified by multi-sample aggregation, even small confidence signals derived from short prefixes can meaningfully influence outcomes in these boundary cases. Building on this insight, we introduce Prefix-Guided Sampling (PreG), a method that reallocates computation by first generating short prefixes, ranking them using internal confidence scores, and then completing only the most promising candidates. This strategy reduces token usage while maintaining gains in path quality. We provide theoretical analysis demonstrating that, under a fixed compute budget, PreG strengthens the effective signal by widening the decision boundary margin. Empirically, our method consistently outperforms standard parallel TTS approaches across benchmarks, while significantly improving token efficiency and reducing overall computation.
Figures & tables
Figure 1: DC-PreG vs. vanilla DC
Figure 2: Studies on the interaction between confidence scores and aggregation using Qwen3-8B [ 36 ] (a) shows problem accuracy distribution of SC as M increases. The point is jittered to show density. Prefix length in (d) is 4096 which is 22% of full path length in (b)(c). (b)(c)(d) fixes M=200 .
Figure 3: PreG framework
QWen3-8B
AIME25
BRUMO
HMMT
CMIMC
GPQA-D
(100k/300k/1000k)
(100k/300k/1000k)
(100k/300k/1000k)
(100k/300k/1000k)
(100k/300k/1000k)
Pass@1
67.94
69.64
45.30
46.14
58.90
Self-Consistency
76.53 / 78.43 / 79.40
76.93 / 78.70 / 79.90
52.37 / 56.10 / 57.33
52.78 / 55.50 / 56.33
68.90 / 69.87 / 70.75
PRM
78.17 / 78.43 / 78.97
78.17 / 78.93 / 80.27
56.60 / 57.00 / 58.10
55.17 / 55.53 / 56.55
67.88 / 68.43 / 69.41
ESC
78.33 / 78.77 / 81.00
77.87 / 79.47 / 80.73
55.87 / 57.13 / 58.03
55.10 / 55.85 / 56.23
69.24 / 70.17 / NA
ST-BoN
75.40 / 78.70 / 80.60
75.13 / 78.00 / 79.73
49.40 / 53.73 / 55.13
49.48 / 54.65 / 56.13
67.77 / 67.34 / 68.92
Table 1: Accuracy under fixed budgets (100k, 300k, 1000k tokens). Results exceeding and falling below the corresponding vanilla baseline are underlined in green and red , respectively. The best result per dataset-budget combination is shown in bold .
Table 5
Figure 4: Effect of k and α on Accuracy (Qwen, Math Datasets)
Figure 5: Tokens vs. Acc.
Method
Traces
Tokens
Latency
Avg. KV
Peak KV
per problem
(M)
(min)
(%)
(%)
DC-Vanilla
32
6.43
58.5
37.2
93.8
DC-PreG
80→24
6.95
40.6
31.3
74.7
Table 4: Multi-GPU inference efficiency on four H200 GPUs using Qwen3-8B.
School of Computer Science and Engineering, Beihang University · 3Hangzhou Innovation Institute, Beihang University · 2Qingdao Research Institute, Beihang University