text-gradients

Tag

Cards List
#text-gradients

From Agent Failures to Text Policies: What Works and What Breaks

arXiv cs.CL · 2026-07-24 Cached

This paper investigates why text-based optimization (TextGrad) fails for language agents, showing that while frozen agents can follow good policies, they cannot reliably learn and select policies from their own trajectories.

0 favorites 0 likes
#text-gradients

When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges

Hugging Face Daily Papers · 2026-05-25 Cached

This paper identifies two failure modes in multi-objective prompt optimization for LLM judges using textual gradients: gradient dilution during optimization and instruction interference during inference, showing that joint gradient processing loses criterion-specific information.

0 favorites 0 likes
← Back to home

Submit Feedback