Hugging Face Blog Compares CUGA, Hermes, and Deep Agents Harnesses
The blog compares CUGA, Hermes, and Deep Agents harnesses for the same model and advises on when to pick each.
Stories per day · 30 days
2 RSS
Relatedappsec2bright-security2coding-agents2fuzzing2qwen2star-fuzzer23d-generation1agentic-reasoning1agents1ai-agents1benchmarks1claude1claude-code1cuga1dataset1deep-agents1developer-framework1developer-tools1
30 stories, newest first · one card per story
Stories tagged #harness
uni-robot-agent harness enables open-weight robot-use agents
Qwen3.8-Flash-Next reaches 31.39 RoboDojo score on open models, surpassing GPT-6 Astra-RoboProbe.
RoboArchitect automates robotic agent harness with persistent memory
Coding model iteratively evolves harness around frozen policies raising success rates 3-4x on unseen scenes and tasks.
Infini-AI-Lab releases open-source Hermit harness adapter for agents
The captured page is a cookie notice, so no features, license terms or availability details are available.
Five Qwen3.8-27B models match Fable 5 with GVS5H harness
The claim is a Hacker News post with 50 points and nine comments; the feed gives no scores or method.
Bright Security launches STAR Fuzzer for agentic harness generation
The vendor says a first research run flagged High or Critical issues in 45% of projects tested.
3
Self-HPO alternates harness and policy updates for coding agents
On Qwen3.5-35B-A3B, average resolve rate rose from 57.8% to 64.8% across three coding benchmarks.
3DCodeVerse: Exploring 3D Worlds as Code
3DCodeVerse pairs a 2M executable-code dataset with a harness that beats Claude Design in tests.
CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness
CoWorld Reasoner lets a VLM call a video world model as a tool, lifting accuracy on all seven reasoning benchmarks.
How to engineer an AI harness for game development
A Calgary talk argues game LLMs need harnesses because much of a game is not code.
7
Self-Evolving Agent Harness
Paper formalizes persistent self-evolution of agent harnesses with fixed weights and validation bounds.
Skill adaptation improves weak models in harness self-evolution
Across 103 task-skill pairs, skills that raise GPT-5.6-luna by 31.1 points lower Gemma-4-E4B by 8.8.
HERA co-evolves agent harnesses to abstain on infeasible tasks
An evolved harness raised abstention accuracy from 61.7% to 83.3% and transferred to 19 other LLMs.
Every SaaS business will become a harness around a model
An essay argues every SaaS company will become a harness around a model and human reviewers.
Academia is for Ambition — Alex Zhang, MIT
MIT's Alex Zhang discusses Recursive Language Models, GPU kernels, and multi-agent harnesses.
Harness-Aware Distillation for Small Language Model Agents
Harness-Aware Distillation trains smaller agents on skills the fixed software harness cannot supply.
Dynamic Harness Search: Building Multi-Agent Systems Per-Query via Prediction
SHIFT searches per-query agent harnesses and beats 17 baselines by 7.2 accuracy points.
VISTA: A Visual Harness for Reasoning in an Interactive World
VISTA's visual-memory harness lifts Claude Opus 5.0 to a perfect ARC-AGI-3 score using 57.4% fewer actions.
Turbo Harness: Instance-Adaptive Harness Optimization
Turbo Harness adapts a global agent harness per task instance and outperforms prior optimizers on seven benchmarks.
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI
A Builder learns reusable meta-skills that improve frozen-model agent harnesses by about nine points on benchmarks.
Google Research Open-Sources RRSI: AI Agents That Improve Their Own Harness Without Overfitting
Google Research open-sourced RRSI, letting frozen-weight agents improve their harness without overfitting benchmarks.
5
MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution
MILO co-evolves agent harnesses and search strategy, beating prior harnesses on Terminal-Bench, PaperBench, and DeepSWE.
Harness Learning Enables Generalizable Test-Time Adaptation
Harness learning trains a proposer to revise an agent's executable harness from execution feedback.
From Migration to Calibration: Preserving Agent Capabilities across Models, Jurisdictions, and Scale
Researchers propose three-layer calibration so agents keep capabilities when models, jurisdictions, or scale change.