cd /news/artificial-intelligence/self-evolving-embodied-agents-via-sk… · home topics artificial-intelligence article
[ARTICLE · art-94713] src=arxiv.org ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

Self-Evolving Embodied Agents via Skill-Harness Evolution

Researchers propose SHAPER, a self-evolving framework that improves embodied agents by evolving reusable skills and a context-code harness without updating model parameters, achieving gains on VLABench and ESI-Bench benchmarks. The framework keeps the model frozen and uses it as both planner and optimizer, offering a practical alternative when training is expensive or unavailable.

read1 min views1 publishedAug 13, 2026

arXiv:2608.11350v1 Announce Type: new Abstract: Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on the skills, context, action interfaces, and execution harness surrounding the model. While supervised fine-tuning and reinforcement learning can adapt agents to new environments, they require additional data, rewards, and training runs; meanwhile, many train-free code-centric approaches rely on programmable robot APIs that may be unavailable in fixed-interface settings. We propose SHAPER, a self-evolving framework for train-free embodied adaptation that keeps model parameters frozen and improves the non-parametric agent system by evolving reusable skills and a context-code harness through target-environment rollouts. In SHAPER, the same frozen model can serve as both planner and optimizer, refining its external skills and context-code harness without parameter updates. We evaluate SHAPER on VLABench and ESI-Bench, covering embodied agents with different low-level action interfaces, and compare against pure execution, supervised fine-tuning, and test-time-scaling baselines such as verifier-free selection and voting. Our results suggest that skill-and-harness optimization is a practical route to self-evolving embodied agents when model training is expensive, unavailable, or undesirable.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @shaper 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/self-evolving-embodi…] indexed:0 read:1min 2026-08-13 ·