An LLM agent can improve itself at test time by rewriting its surrounding executable harness from unlabeled traces, using only proxy signals and a frozen model.
Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution , booktitle =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
The paper maps agent memory research via three forms (token-level, parametric, latent), three functions (factual, experiential, working), and dynamics of formation/evolution/retrieval, plus benchmarks and future directions.
Active information seeking via search tools, when combined with multi-candidate context pruning during training, produces consistent gains on translation, health, and reasoning tasks over naive tool addition or no-tool baselines.
citing papers explorer
-
TTHE: Test-Time Harness Evolution
An LLM agent can improve itself at test time by rewriting its surrounding executable harness from unlabeled traces, using only proxy signals and a frozen model.
-
Memory in the Age of AI Agents
The paper maps agent memory research via three forms (token-level, parametric, latent), three functions (factual, experiential, working), and dynamics of formation/evolution/retrieval, plus benchmarks and future directions.
-
Context Training with Active Information Seeking
Active information seeking via search tools, when combined with multi-candidate context pruning during training, produces consistent gains on translation, health, and reasoning tasks over naive tool addition or no-tool baselines.