Pith. sign in

Optimizing instructions and demonstrations for multi-stage language model programs

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.LG 1

years

2026 2

representative citing papers

When Does Continual Learning Require Learning

cs.LG · 2026-07-08 · conditional · novelty 6.0

Different patterns of environmental change (space vs time) require different LLM update behaviors; no single family of methods—prompts, distillation, RL, or compression—handles all regimes.

citing papers explorer

Showing 2 of 2 citing papers.

  • Back to the Beginning of Heuristic Design: Bridging Code and Knowledge with LLMs cs.AI · 2026-05-07 · unverdicted · none · ref 59

    A knowledge-first approach to LLM-driven automatic heuristic design in combinatorial optimization yields better discovery efficiency, transfer, and generalization than code-centric baselines by formalizing a distortion-compression trade-off.

  • When Does Continual Learning Require Learning cs.LG · 2026-07-08 · conditional · none · ref 44

    Different patterns of environmental change (space vs time) require different LLM update behaviors; no single family of methods—prompts, distillation, RL, or compression—handles all regimes.