RECAP benchmark finds that six prompt optimization methods show no significant performance gains under proactive continual adaptation to evolving constraints across four LLMs.
Dynamic cheatsheet: Test-time learning with adaptive memory
3 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
3
Pith papers citing it
1
external citations · OpenAlex
years
2026 3verdicts
UNVERDICTED 3representative citing papers
FluxMem evolves memory as a heterogeneous graph via three refinement stages and reports consistent state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.
Priority ranking offers a low-cost direct evaluation for harness optimizers that correlates with their real multi-step optimization performance, supported by the Shor dataset of 182 scenarios.
citing papers explorer
-
RECAP: Regression Evaluation for Continual Adaptation of Prompts
RECAP benchmark finds that six prompt optimization methods show no significant performance gains under proactive continual adaptation to evolving constraints across four LLMs.
-
Rethinking Memory as Continuously Evolving Connectivity
FluxMem evolves memory as a heterogeneous graph via three refinement stages and reports consistent state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.
-
Towards Direct Evaluation of Harness Optimizers via Priority Ranking
Priority ranking offers a low-cost direct evaluation for harness optimizers that correlates with their real multi-step optimization performance, supported by the Shor dataset of 182 scenarios.