TL;DR
PRISM is a stable model-agnostic framework that treats prompt optimization as a multi-candidate selection process instead of single-shot refinement, enabling more stable improvements and demonstrating the effectiveness of PRISM in practical settings.
STEVE, a stabilization framework with two coupled mechanisms that reduces degradation and produces more robust prompts, provides a practical way to improve the stability and effectiveness of textual-gradient prompt optimization.
Results suggest that corpus-scale statistical reflection is a viable alternative to iterative search for prompt optimization, and given only a static corpus of agent trajectories, an off-the-shelf coding agent can directly synthesize an optimized prompt, requiring neither environment access nor validation data.
ESO (Error-Structured Prompt Optimization), which decomposes prompt optimization into three phases: Diagnose clusters all training errors into structural patterns in one round; generate candidates via four complementary strategies with independent biases; Select applies bootstrap stability selection.
This paper introduces SEPO (Structural, Evidence-grounded Prompt Optimization), a multi-trajectory prompt optimiser centred on edit-effect lineage feedback that makes prompt optimisation addressable, attributable, and actionable.
Efficient multimodal instruction tuning requires reducing both training data volume and computational cost without substantially sacrificing downstream performance. Existing data selection methods can remove redundancy but cannot repair imperfect supervision or supplement under-represented capabilities. We propose SANe...
This work introduces CAPO (Constraint-Aware Prompt Optimization), a primal-dual method that combines pool-based rewrites with adaptive constraint weighting to optimize system prompts under explicit operational constraints.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
