StickyInvoc introduces sticky tasks that load LLM model state once and invocation tasks that reuse it, yielding 3.6x speedup on a 150k-inference workflow.
A strategic coordination framework of small llms matches large llms in data synthesis,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
POLIS gets 1-4B parameter language models to verify each other's math answers, store the good ones in shared memory, and fine-tune on them, reporting big average gains, but the protocol is underspecified.
citing papers explorer
-
StickyInvoc: Rethinking Task Models for High-throughput Workflows in the LLM Era
StickyInvoc introduces sticky tasks that load LLM model state once and invocation tasks that reuse it, yielding 3.6x speedup on a 150k-inference workflow.
-
The Ratchet Effect in Silico: How Interaction Drives Cumulative Intelligence in Large Language Models
POLIS gets 1-4B parameter language models to verify each other's math answers, store the good ones in shared memory, and fine-tune on them, reporting big average gains, but the protocol is underspecified.
- Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy