AgentSLABench

What is AgentSLABench?

A resource-aware agent benchmark with 16 Dockerized task environments that profiles correctness alongside latency, cost, compute, memory, and network use under…

Released

2026-08-01

Evaluates

Agents & Tool Use, Software & AI Compute, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.00805

AgentSLABench paper and code

• Paper https://arxiv.org/abs/2608.00805
• Code https://github.com/MeherBhaskar/agentslabench

Which sources cite AgentSLABench?

• AgentSLABench

Related Agents & Tool Use, Software & AI Compute, cs.AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• Active-SWE
• AdaPlanBench
• Adaptive Adversaries
• ADeptS-Bench