Concept · 14 episode(s)

Agent Scaffolding

← all concepts

Definition

Agent scaffolding is the control flow wrapped around a language model that turns it into an agent: the prompt structure, tool-call loop, retry logic, planning steps, and memory plumbing. Two agents built on the same base model can perform very differently depending on scaffolding, which makes it a major confound in capability evaluations.

Episodes covering this

  1. 076
    Same Model, Organized Differently: How an Agent Architecture Beat Frontier Systems at Research Math
    Zhao, Yuan, Choi et al. · Georgia Institute of Technology·22 min·May 25, 2026
  2. 071
    When the Model Is Fine and the Plumbing Is Broken: Fixing Agents at the Interface
    Xu, Wen, Li · Peking University·23 min·May 22, 2026
  3. 063
    Why Web Agents Are Slow: A Compiler-Style Fix for Computer-Use Latency
    Winston, Wang, Mirhoseini et al. · Stanford University·26 min·May 21, 2026
  4. 062
    Treating Hallucinations as Exploits: A Gate-Based Architecture for Agent Safety
    Zhang, Zheng, Yang · Shenzhen University·24 min·May 20, 2026
  5. 061
    When Helpful Agents Go Sideways: A 404 Error, Campus Security, and Why Alignment Misses This
    Jha, Triedman, Bhattacharya et al. · Cornell University·27 min·May 20, 2026
  6. 053
    An AI Agent Swapped In Focal Loss And Beat A Human-Tuned Training Script
    Pepe, Lin, Magka et al. · FAIR at Meta·32 min·May 18, 2026
  7. 051
    Why Parallel Sampling Plateaus, And What Evidence Graphs Do Instead
    Zhang, Su, Chen et al. · MiroMind AI·22 min·May 18, 2026
  8. 047
    When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
    Peng, Yao, Wu et al. · Microsoft Research·28 min·May 15, 2026
  9. 046
    When the AI Optimizer Edits the Grade Book: Why Harnessing Evolution Needs a Wall
    Zhang, Gu, Ruan et al. · The Hong Kong University of Science and Technology (Guangzhou) / DeepWisdom·24 min·May 15, 2026
  10. 034
    Catching Multi-Agent Deadlocks Before Deployment With a 40-Year-Old Tool
    Xia, Li, Ehsan et al. · Rutgers University·30 min·May 11, 2026
  11. 030
    Why Your AI Agent Won't Stop Working — and Each Model Falls for a Different Trap
    Xu, Wang, Zhang et al. · Zhejiang University·30 min·May 09, 2026
  12. 027
    When AI Agents Build the Serving Stack: A Bet on Bespoke Infrastructure
    Kamahori, Li, Peter et al. · University of Washington·30 min·May 08, 2026
  13. 024
    An AI Agent That Found 28 Zero-Days in Windows — And What Made It Work
    Lee, Kim, Zhang · University of Illinois at Urbana-Champaign·22 min·May 07, 2026
  14. 012
    Why AI Coding Agents Keep Trying to Debug Without a Debugger
    Liu, Wang, Chen et al. · Sun Yat-sen University·21 min·May 02, 2026

Worth reading next

Papers we haven't done a deep dive on yet, but would recommend on this topic.