Multi-agent LLM systems rely on generative models for expert execution, workflow planning, and artifact review. Yet many coordination operations require only bounded decisions, such as selecting the next expert or judging artifact quality. Profiling three representative MAS frameworks, we find that routing and review account for 31.7-43.5% of generative-LLM tokens. However, replacing these operations with low-cost decision models introduces two interface gaps: generative planners produce execution plans and handoff instructions (planning gap), while reviewers provide actionable feedback for repairing flawed artifacts (review gap), which bounded decisions alone cannot provide. We introduce Jev-LiteMAS, a multi-agent framework that bridges both gaps by combining a lightweight decision model (Jev) with generative execution and feedback. To address the planning gap, Jev selects experts dynamically from the task and prior expert outputs, using accumulated context to ground subsequent execution without a pre-generated trajectory. To address the review gap, Jev screens intermediate artifacts against task criteria: passing artifacts proceed directly, whereas flagged ones undergo LLM re-review for acceptance or corrective feedback. Across four benchmarks and two backbones, Jev-LiteMAS reduces generative-LLM tokens by 12.7-54.6% over LAS, maintaining accuracy within 1.34 percentage points and lowering latency in seven of eight settings. Grounding routing in substantive expert outputs prevents up to 18.0 points in accuracy loss.
Figures & tables
Figure 1. Routing and review account of generative-LLM tokens and latency in our measured MAS configurations. Each bar is normalized by the total cost of its framework and across two benchmarks.
Figure 2. Overview of Jev-LiteMAS.
DeepSeek-V4-Flash
Method
MATH
MBPP+
ACC ↑
Input
Output
Total ↓
E2E ↓
Calls ↓
ACC ↑
Input
Output
Total ↓
E2E ↓
Calls ↓
Single-agent
85.33
1234.8
944.7
2179.5
10.70
1.00
66.67
1257.6
632.8
1890.4
14.70
1.00
MetaGPT
98.67
6754.1
3240.9
9995.0
36.07
4.00
82.67
7292.1
5774.8
13066.9
66.36
4.00
AFlow
86.67
2248.9
1667.2
3916.1
17.09
1.00
73.33
2305.5
2906.9
5212.4
19.90
1.00
AgentNet
96.67
3256.4
4467.6
7724.0
29.03
2.67
78.00
3610.7
4623.7
8234.4
43.91
3.13
Table 1. End-to-end comparison across four benchmarks using DeepSeek-V4-Flash (top) and GPT-5 (bottom). ACC is in percent; Input, Output, and Total denote generative-LLM token counts; E2E is wall-clock latency in seconds; Calls denotes generative-LLM API calls per evaluation unit. Arrows indicate preferred directions.
IDRBench I3
API-Bank
Method
ACC
Tok.
E2E
Calls
ACC
Tok.
E2E
Calls
Static
74.00
14.603
79.00
4.00
61.80
15.178
35.71
4.00
Heuristic
58.67
9.414
56.34
2.45
64.27
7.564
31.53
3.49
Planner-Replan
48.00
28.566
96.79
5.54
53.93
21.873
47.65
8.31
Jev-LiteMAS
75.33
10.233
72.40
2.47
66.29
9.869
35.34
4.00
Table 2. Ablations of workflow organization and routing on IDRBench I3 and API-Bank. ACC is accuracy (%); Tok. counts generative-LLM tokens (K), excluding decision-model tokens; E2E is latency (s), and Calls counts generative-LLM API requests. SLM Router uses Qwen3-1.7B-Instruct. Content-Blind masks substantive expert and tool outputs only in the router input while preserving task information, legal actions, execution metadata, and inter-expert communication.
MATH
MBPP+
Method
ACC ↑
Tok. ↓
E2E ↓
ASR ↓
ACC ↑
Tok. ↓
E2E ↓
ASR ↓
Clean-MAS
96.67
6,752
26.77
–
86.00
7,794
45.92
–
Attack-MAS
46.67
6,389
24.62
50.00
39.33
6,973
46.84
48.67
MAD
98.00
20,563
73.76
0.00
85.33
28,705
98.76
1.33
G-Safe
69.33
6,884
31.33
27.34
52.00
6,996
55.32
35.33
MAS-Shield
91.33
9,746
40.51
5.33
78.67
11,324
67.76
8.67
Table 3. Review robustness under injected agent errors on MATH and MBPP+. ACC(%) and ASR(%); Tok. denotes generative-LLM tokens; E2E is end-to-end latency (s). A dash denotes runs without injected errors.
Case
Judge
ACC
Rate
Tok.
E2E
MATH Clean
Jev
97.33
4.00
5,433
22.13
LLM Judge
96.67
1.33
7,691
35.44
SLM Judge
98.00
0.00
5,135
23.32
MATH Attack
Jev
94.00
95.33
8,657
34.19
LLM Judge
94.67
96.67
10,138
45.14
SLM Judge
68.67
61.33
7,149
42.33
Table 4. Jev, LLM, and SLM judging under clean and injected-error conditions. ACC and Rate are percentages; Rate denotes FPR ( ↓ ) for clean cases and TPR ( ↑ ) for attacks. Tok. counts generative-LLM tokens only; E2E is latency (s). SLM uses Qwen3-1.7B-Instruct.
Figure 3. Latency and estimated model-cost breakdown of Jev-LiteMAS with GPT-5 experts and Jev routing across four benchmarks. (a) End-to-end latency and its GPT-5/Jev request-time components; (b) GPT-5 and Jev API fees.
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
IDRBench I3
API-Bank
Setting
ACC ↑
Tok. ↓
E2E ↓
Calls ↓
ACC ↑
Tok. ↓
E2E ↓
Calls ↓
(a) Generative-LLM call budget
B=2
46.67
7.637
43.86
2.00
56.18
10.713
16.12
2.00
B=3
62.67
9.496
56.01
2.26
57.08
12.040
20.63
2.93
B=4
70.00
10.514
68.19
2.48
64.72
14.553
18.34
3.96
B=6
73.33
11.298
71.88
2.64
65.84
12.817
20.16
4.46
Appendix
Table 5. Sensitivity to generative-LLM call budgets and heterogeneous expert backbones on IDRBench I3 and API-Bank. ACC is in percent; Tok. denotes total generative-LLM tokens in thousands; E2E denotes end-to-end latency in seconds; Calls denotes average generative-LLM API calls. In (b), AAA uses one backbone throughout, ABB switches backbone at the first expert handoff, and ABA switches at every handoff.