proomt

Search

Search posts, papers, and topics

All posts

Hugging Face Daily PapersHongyang Du, Lan Yan, Christian Flores1 min readpaperadvanced

Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design

Read on arxiv.org

Summary

The paper introduces Designer‑RSI, a continual‑adaptation system that couples a frozen design‑software‑controlling LLM with an external procedural memory of natural‑language design skills. Over five adaptation rounds on real user briefs, the memory grows from 76 to 139 procedures and lifts execution success from 72.7% to 99.3%, showing that skill accumulation and selective replay can dramatically…

  • Procedural memory stores reusable NL‑to‑action scripts that are widened (new tasks) and deepened (revision) based on execution outcomes.
  • A replay gate only accepts memory updates that fix failures without degrading previously successful executions.
  • No model weight updates are needed; the system improves solely via the external skill bank, achieving 99.3% success on GenEval2.
  • Combining widening and deepening yields a statistically significant 58.5% win rate over a no‑skill baseline on held‑out briefs.

Engineers building AI agents for creative or tool‑heavy domains need a way to keep improving from noisy user interactions without costly retraining.

8/10
llmmachine learningml infracontinual learningprocedural memory

Related reading

  1. Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

    Code2Skill is an automated pipeline that mines popular GitHub repositories to extract verifiable, implementation‑anchored procedural “skills”. It builds a bank of ~1 M skill records (atomic ops, workflows, patterns) with provenance metadata, verifies each via blind reconstruction, and shows that augmenting LLM‑based agents with these skills yields an average 11.7% performance lift across 72 proto…

    Hugging Face Daily Papersarxiv.org1 minpaper

  2. Shared Selective Persistent Memory for Agentic LLM Systems

    Apple proposes a memory architecture for agentic LLMs that selectively persists reusable context (specs, schemas, configs, constraints) across sessions and users. Shared workspaces with role‑based access and a zero‑token data‑refresh mechanism cut token usage by 97×, reduce task time by 14×, and raise task‑completion rates to 96% versus 71%‑79% for baselines.

    Apple Machine Learning Researchapple.com1 minpaper

  3. OmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning

    OmniHarness introduces a symbolic‑policy framework that extracts reusable procedural knowledge from multimodal LLM‑driven visual generation runs. By decoupling task logic from instance inputs, the system can instantiate, adapt, and compose policies for new visual tasks, using intermediate verification for on‑the‑fly refinement while keeping the underlying model frozen. Self‑directed practice task…

    Hugging Face Daily Papersarxiv.org1 minpaper

  4. Agentic Skill Decay

    Addy Osmani warns that AI agents can short‑circuit the hands‑on practice (“reps”) that builds deep expertise and judgment. He recommends deliberately inserting hypothesis‑forming, “why” questioning, diff inspection, failure prediction, and occasional manual coding into the workflow, especially for junior engineers. A 2026 Anthropic study showed junior developers using AI scored 17 % lower on a fo…

    Addy Osmaniaddyosmani.com16 min

  5. Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents

    EvoSkill‑GUI lets GUI agents revise their procedural skills on‑the‑fly without extra training by using a reflect‑revise‑reuse loop that edits skill packages during execution. The approach yields up to +16.2% improvement on MobileWorld and similar gains on AndroidWorld and OSWorld, and the evolved skills transfer to related tasks.

    Hugging Face Daily Papersarxiv.org1 minpaper

  6. Changing the game: How Google uses agentic AI to secure hundreds of millions of lines of code

    Google’s AI & Infrastructure team built an agentic pipeline (Mantis) that runs pre‑submit AI‑driven scans on every code check‑in, validates findings with a fast triage agent (AST + call‑graph analysis) achieving >92% precision in <1 min, then auto‑generates fixes via a bug‑fix agent. Localized threat models and a two‑step scan cut false‑positives to ~3% and prevent hundreds of vulnerabilities eac…

    Google Cloud Bloggoogle.com4 min