cd /news/large-language-models/are-online-skill-and-memory-modules-… · home topics large-language-models article
[ARTICLE · art-28955] src=arxiv.org ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Are Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents

A new study finds that online web agents augmented with memory, workflow, or skill modules often fail to outperform a token-matched vanilla baseline under a fixed inference budget. Testing across three models and multiple domains, researchers show that the apparent gains of augmentation methods vanish when controlling for token costs, and they recommend reporting run-to-run variance as a core evaluation criterion.

read1 min views1 publishedJun 16, 2026

arXiv:2606.15017v1 Announce Type: new Abstract: Online web agents often augment a base actor with memory, workflow, or skill modules. These modules can improve performance, but they also consume test-time tokens, a cost rarely reported alongside the actor's inference cost. We study online augmentation, where this overhead is paid on every task, and re-evaluate its benefits under a fixed total inference budget. We compare AWM, ASI, and ReasoningBank with a token-matched vanilla baseline that uses the same budget for additional actor steps. Across three WebArena domains and three models, Gemini 3 Flash, GPT-5.4-mini, and Qwen 3.6-27B, the vanilla baseline matches or surpasses all three augmentation methods in aggregate success rate while often using fewer total tokens. We observe a similar trend on WorkArena-L1 with Qwen 3.6-27B, indicating that the effect extends to enterprise knowledge-work tasks. Our results suggest that skills and workflow memory can be useful in specific domains, but their apparent gains often vanish against a budget-matched actor. We further show that run-to-run variance materially affects outcomes and should be reported as a core evaluation criterion for online web agents.

── more in #large-language-models 4 stories · sorted by recency
── more on @gemini 3 flash 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/are-online-skill-and…] indexed:0 read:1min 2026-06-16 ·