Why More Experience Made This AI Agent Worse, And How to Fix It

Why More Experience Made This AI Agent Worse, And How to Fix It Source: https://arxiv.org/abs/2606.15390 Paper was published on June 13, 2026 This episode was AI-generated on June 16, 2026. The script was written by an AI language model and the host voices were synthesized by Eleven Labs. The producer is not affiliated with Anthropic or Eleven Labs. An AI agent that kept a notebook of hard-won lessons performed worse than one with no notebook at all, because over 90% of its skills helped on some tasks and quietly hurt on others. This paper borrows the logic of randomized clinical trials to measure where each skill actually helps, then shows the biggest gain comes not from curating the library but from deciding which skills each task is allowed to see. Key Takeaways: - Why bad agent skills hide in plain sight: they help on some tasks and hurt on others, so their average effect looks harmless near zero - How the authors adapt randomized controlled trials to measure a skill's true causal effect, building a green-and-red attribution matrix across skills and tasks - Why deleting harmful skills is the wrong move, and why per-task masking, not library cleanup, drives the biggest performance jump (7.5 points vs. 2) - The reverse-masking control that proves it's removing harmful skills, not just shortening the prompt, that helps - Where the method breaks down: it buys nothing for already-strong frontier models, and its per-skill measurements are statistically underpowered by the authors' own admission - The headline result: a new state of the art on AppWorld's hardest split without any weight retraining, plus a documented case where an uncurated library made an agent strictly worse 00:00 - The coffee grinder that broke the agent: An agent fails a simple Amazon task because of a stray Spotify rule in its notebook, setting up the paper's core puzzle about accumulated skills. 03:09 - The popular recipe and its unchecked assumption: How self-improving agents distill lessons into plain-English skills, and why nobody verified whether those skills actually help across many tasks. 06:18 - Why averages hide bad skills: The concept of causal heterogeneity, where a skill helps on some task types and hurts on others so its average effect cancels out to near zero. 09:27 - Randomized trials for an agent's memory: Borrowing the clinical-trial idea of randomization to measure each skill's true causal effect and build the attribution matrix, while handling skill interdependence. 12:37 - Why you can't just delete bad skills: Because harm is conditional, the fix is conditional too: offline the library gets restructured by splitting heterogeneous skills into triggered variants. 15:46 - Per-task masking and the parachute principle: At inference time the system predicts a skill's effect from similar past tasks and conservatively masks likely-harmful ones, distinguishing relevance from helpfulness. 18:55 - What works and where the gains come from: The ablation showing masking, not library curation, is the biggest lever, plus headline results on AppWorld and a documented regression that the method reverses. 22:05 - The critique and the shelf life: Underpowered per-skill statistics, thin task coverage, smuggled-in LLM judgment for splitting, and the finding that strong frontier models gain nothing. 25:14 - What actually changes: Why this layers onto existing skill pipelines at inference time, and the mental-model flip from accumulation to reading the room. Recommended Reading: - AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents: The benchmark this episode's headline results are measured on, where the curated skill library produced its biggest gains on the hardest task tier. (https://arxiv.org/abs/2407.18901) - Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks: The foundational RAG paper whose 'relevance equals helpfulness' assumption the episode directly attacks, arguing topically relevant skills can still cause harm. (https://arxiv.org/abs/2005.11401) - Voyager: An Open-Ended Embodied Agent with Large Language Models: A canonical example of the 'accumulate a growing skill library' paradigm this episode critiques for letting the same model generate, keep, and apply skills by its own judgment. (https://arxiv.org/abs/2305.16291) - Reflexion: Language Agents with Verbal Reinforcement Learning: An influential take on agents distilling natural-language lessons from experience, the exact self-improvement recipe whose hidden toxicity the episode examines. (https://arxiv.org/abs/2303.11366)