Airavat: An Agentic Framework for Internet Measurement

Alagappan Ramanathan; Eunju Kang; Dongsu Han; Sangeetha Abdu Jyothi

cs.NIFeb 24, 2026

Airavat: An Agentic Framework for Internet Measurement

Authors: Alagappan Ramanathan, Eunju Kang, Dongsu Han, Sangeetha Abdu Jyothi

Organizations: University of California, Irvine · KAIST

Abstract

Internet measurement faces twin challenges: complex analyses require expert-level orchestration of tools, yet even syntactically correct implementations can have methodological flaws and can be difficult to verify. Democratizing measurement capabilities thus demands automating both workflow generation and verification against methodological standards established through decades of research. We present Airavat, the first agentic framework for Internet measurement workflow generation with systematic verification and validation. Airavat coordinates a set of agents mirroring expert reasoning: three agents handle problem decomposition, solution design, and code implementation, with assistance from a registry of existing tools. Two specialized engines ensure methodological correctness: a Verification Engine evaluates workflows against a knowledge graph encoding five decades of measurement research, while a Validation Engine identifies appropriate validation techniques grounded in established methodologies. Through four Internet measurement case studies, we demonstrate that Airavat (i) generates workflows matching expert-level solutions, (ii) makes sound architectural decisions, (iii) addresses novel problems without ground truth, and (iv) identifies methodological flaws missed by standard execution-based testing.

Figures & tables

Figure 1. Airavat’s architecture comprising a multi-agent workflow generation pipeline, verification engine, validation engine, knowledge graph, and registry.

Case Study	Problem	LoC	Key Capability	Results
1: Cable Impact	SeaMeWe-5 failure	$\sim$ 850	Expert Solution Replication	Matches the expert solution
2: Disaster	Earthquake/hurricane	$\sim$ 700	Workflow Simplicity	Appropriate expert-level minimal solution
3: Cascading	Europe-Asia cables	$\sim$ 1600	9-function orchestration	Multi-layer integration framework
4: Prefix2Org	Prefix-to-org mapping	1500 $\rightarrow$ 1700	Domain Transferability +	0% $\rightarrow$ 70-75% (vague query);
		(w/ verification)	Verification capabilities	0% $\rightarrow$ 90.9% tags (improved query)

Table 1. Case Study Summary

Figure 2. Country-level impact from SeaMeWe-5 cable failure. The heatmap shows the risk factor, computed as the fraction of IP addresses affected in a country relative to the total number of IP addresses mapped to that country. The results match the findings of Xaminer ( Ramanathan et al., 2024 ) .

Figure 3. Global cable infrastructure impact from earthquakes and hurricanes. The heatmap shows the risk factor, computed as the fraction of IP links affected in a country relative to the total number of IP links in that country. The results match the findings of Xaminer ( Ramanathan et al., 2024 ) .

Component	Cost per Run	Notes
Agent 1 (QueryMind)	$0.06 -$ 0.15	Query decomposition
Agent 2 (WorkflowScout)	$0.25 -$ 0.60	Workflow specification
Agent 3 (SolutionWeaver)	$0.35 -$ 0.60	Code generation
Agent 4 (RegistryCurator)	$0.20 -$ 0.40	Quality assessment
Standard Workflow	$0.80 -$ 1.70	Agents 1-3 only
Verification Synthesizer	$0.50 -$ 0.70	Standard mode

Table 2. Cost Analysis Summary

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Case Study	Registry Functions by System
Cable Impact	nautilus_system: (1) get_nautilus_link_to_cable_mapping (2) get_lp_id_to_country_dict (3) get_ip_to_geolocation_mappings (4) get_ip_to_asn_mappings
Disaster Impact	nautilus_system: (1) get_nautilus_link_to_cable_mapping (2) get_lp_id_to_country_dict (3) get_ip_to_geolocation_mappings (4) get_ip_to_asn_mappings xaminer_system: (5) generate_cable_segments_to_all_info_map (6) generate_cable_segment_to_country_as_maps (7) process_single_event
Cascading Effects	nautilus_system: (1) get_nautilus_link_to_cable_mapping (2) get_lp_id_to_country_dict (3) get_ip_to_geolocation_mappings (4) get_ip_to_asn_mappings xaminer_system: (5) generate_cable_segments_to_all_info_map (6) generate_cable_segment_to_country_as_maps (7) process_single_event submarine_system: (8) get_country_to_cable_graph as_dependency_system: (9) get_as_dependency_graph
Prefix2Org	bgp_system: (1) download_bgp_dumps whois_system: (2) parse_whois_dump rpki_system: (3) get_rpki_snapshot as2org_system: (4) get_as2org_mappings

Appendix

Table 3. Registry functions utilized across case studies.

Parameter	Value	Component	Purpose
Novelty threshold (high)	0.7	Evaluator - Stage 2	Problems above classified as novel
Novelty threshold (low)	0.4	Evaluator - Stage 2	Problems below classified as well-studied
Infeasibility threshold	60	Evaluator - Stage 2	Sub-dimension scores below this trigger rejection
Excellence threshold	85	Selector	Workflows above approved directly
Good range lower bound	80	Selector	Workflows below always require synthesis
Structural diversity threshold	0.4	Selector	Triggers complementarity analysis

Appendix

Table 4. Verification Engine parameters.

Figure 7. Europe-Asia Cable Failure Cascade Analysis Workflow (Data Input Layer)

Figure 8. Europe-Asia Cable Failure Cascade Analysis Workflow (Core Processing Layer)

Figure 9. Europe-Asia Cable Failure Cascade Analysis Workflow (Integration & Cascade Layer)

Figure 10. Europe-Asia Cable Failure Cascade Analysis Workflow (Output Reporting Layer)

Agentic Workflows

Agentic workflows coordinate AI agents, tools, and humans across multi-step tasks, emphasizing reliable execution, efficiency, and oversight.

See all 218 papers

WebForge: Breaking the Realism-Reproducibility-Scalability Trilemma in Browser Agent Benchmark
Apr 13, 2026Peng Yuan, Yuyang Yin, Yuxuan Cai +1Web Agent Benchmarks Benchmark Design
Tencent BAC · Tsinghua University
Emergence WebVoyager: Toward Consistent and Transparent Evaluation of (Web) Agents in The Wild
Mar 30, 2026Deepak Akkil, Mowafak Allaham, Amal Raj +2Agent Evaluation Web Agent Benchmarks
Emergence AI · Northwestern University
AgentProofBench: Benchmarking Reusable Verifiers for Web Agents
Oct 25, 2026Jingjie Ning, Xueqi Li, Yi Lu +1LLM Agent Verification Web Agent Benchmarks

Apr 13, 2026J/K move · Enter open · S save

WebForge: Breaking the Realism-Reproducibility-Scalability Trilemma in Browser Agent Benchmark

Peng Yuan, Yuyang Yin, Yuxuan Cai, Zheng Wei

Tencent BAC · Tsinghua University

Web Agent Benchmarks Benchmark Design AI Agent Evaluation Synthetic Benchmark Generation

Open paper AskPDF arXiv

Existing browser agent benchmarks face a fundamental trilemma: real-website benchmarks lack reproducibility due to content drift, controlled environments sacrifice realism by omitting real-web noise, and both require costly manual curation that limits scalability. We present WebForge, the first fully automated framework that resolves this trilemma through a four-agent pipeline -- Plan, Generate, Refine, and Validate -- that produces interactive, self-contained web environments end-to-end without human annotation. A seven-dimensional difficulty control framework structures task design along navigation depth, visual complexity, reasoning difficulty, and more, enabling systematic capability profiling beyond single aggregate scores. Using WebForge, we construct WebForge-Bench, a benchmark of 934 tasks spanning 7 domains and 3 difficulty levels. Multi-model experiments show that difficulty stratification effectively differentiates model capabilities, while cross-domain analysis exposes capability biases invisible to aggregate metrics. Together, these results confirm that multi-dimensional evaluation reveals distinct capability profiles that a single aggregate score cannot capture. Code and benchmark are publicly available at https://github.com/yuandaxia2001/WebForge.

Abstract

Agentic Workflows

Explore similar work

WebForge: Breaking the Realism-Reproducibility-Scalability Trilemma in Browser Agent Benchmark

Emergence WebVoyager: Toward Consistent and Transparent Evaluation of (Web) Agents in The Wild

AgentProofBench: Benchmarking Reusable Verifiers for Web Agents