Study traces GEPA merge instability to configuration, not the operator
A nine-configuration sweep across five datasets finds merge can help both gpt-4.1-mini and Qwen3-8B.
Stories per day · 30 days
3 RSS
4 stories, newest first · one card per story
Stories tagged #ablation
Every Ablation Is a Dose: Counterweights and the Semblance of Self-Repair
Language-model self-repair is explained as pre-existing counterweights following an affine response to ablation dose.
Rethinking Circuit Evaluation: Do Circuits Explain Model Errors?
Circuits that match GPT-2's correct answers often fail to reproduce most of its errors.
Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments
Researchers extend the SwiftSage dual-process agent with adaptive memory and self-reflection modules, improving scores in interactive environments.