HEAL mitigates entropy collapse in few-shot RLVR by selectively adding general-domain data and aligning trajectory-level entropy dynamics, matching full-shot performance with 32 target samples.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
HippoSpark is a state-level on-demand experience retrieval system for LLMs that outperforms task-level experience baselines on mathematical, scientific, and programming benchmarks.
citing papers explorer
-
HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment
HEAL mitigates entropy collapse in few-shot RLVR by selectively adding general-domain data and aligning trajectory-level entropy dynamics, matching full-shot performance with 32 target samples.
-
HippoSpark: An On-Demand Experience System for LLM Reasoning
HippoSpark is a state-level on-demand experience retrieval system for LLMs that outperforms task-level experience baselines on mathematical, scientific, and programming benchmarks.