Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification
Agent harnesses shape how language-model agents use instructions, tools, and runtime components, but adapting these harnesses requires costly verification. Existing propose-and-verify methods typically score every candidate on a fixed task set, wasting rollouts on unrelated behaviors and allowing aggregate scores to obscure specific regressions. We introduce HarnessLens, a budget-aware framework for automated harness evolution. HarnessLens jointly explores the task space and user-configurable components, derives candidate modifications from execution trajectories, and selectively verifies each
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 55%Pluggable by design: An agent mesh for software modernization that adopts the next model release →
- FuzzySimilar title/name (fuzzy) · 87%strands-agents/harness-sdk →
“Fuzzy title match (0.94): “Verify Smarter, Evolve Further: Efficient Harness Evolution ” ≈ “strands-agents/harness-sdk””
- FuzzySimilar title/name (fuzzy) · 59%browser-use/browser-harness →
“Fuzzy title match (0.73): “Verify Smarter, Evolve Further: Efficient Harness Evolution ” ≈ “browser-use/browser-harness””
- LinkedLinked via arxiv author · 85%Jinghan Xu →
“Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification”
- LinkedLinked via arxiv author · 85%Yikai Zhang →
“Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification”
- LinkedLinked via arxiv author · 85%Aili Chen →
“Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification”
- LinkedLinked via arxiv author · 85%Weiyuan Li →
“Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification”
- LinkedLinked via arxiv author · 85%Jiaqing Liang →
“Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification”