Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

DarwinX: Evolving Agent Harnesses via Natural Selection Boosts Benchmarks

AI By Crimson AI Hugging Face Papers 14 August 2026 · 00:00 20 views
Share: X Telegram

Hugging Face researchers introduce DarwinX, a method that evolves agent harnesses through population selection with frozen models, improving verified performance across benchmarks without benchmark-specific patches.

DarwinX: Evolving Agent Harnesses via Natural Selection Boosts Benchmarks

Key points

Hugging Face researchers have unveiled DarwinX, a novel approach to AI agent self-improvement that treats evolution as a selection process over a population of agent harnesses—prompts, tools, skills, and control flow—while keeping the underlying model frozen. This method addresses the limitations of single-lineage search, which often leads to path-dependent results and regressions on other tasks.

DarwinX employs a 'preserve-and-extend' contract, allowing only variants that expand coverage without causing regressions. An archive maintains alternative lineages for recombination, and failure-, teacher-, and self-derived evidence share a unified edit interface. Fitness is determined by each benchmark's own verifier, eliminating the need for gold solutions or hand-picked winners.

Across four benchmarks, DarwinX added an average of about 17 points. Notable results include Terminal-Bench 2.1 rising from 75.5% to 83.2% on GPT-5.5, surpassing Codex's 83.1%, and reaching 84.7% on a stronger base. TerminalWorld's held-out split achieved 68.3%, ahead of all off-the-shelf agents, while WebArena-Infinity real-task pass@1 jumped from 43.5% to 93.0% audit-clean. A Terminal-Bench 2.1 harness transferred unchanged to SWE-bench Verified, improving from 80.8% to 84.2%.

The researchers highlight two unexpected findings: the in-loop proxy saturates while held-out performance lags, and the best-fitting variant is not the best generalizer. This underscores the importance of maintaining a population rather than following a single best lineage. Additionally, an audit of WebArena-Infinity trajectories revealed that the gap between DarwinX and the base agent widens under scrutiny, confirming the robustness of the evolved harnesses.

BenchmarkBaseDarwinXNotes
Terminal-Bench 2.175.5%83.2%avg@5 on GPT-5.5; 84.7% on GPT-5.6 Sol
TerminalWorld61.0%68.3%pass@1 on Opus 4.8, 41 held-out tasks
WebArena-Infinity43.5%93.0%audit-clean pass@1 on 1,260 real tasks
SWE-bench Verified80.8%84.2%zero-shot transfer of terminal harness
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

0
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

0
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

0