activity
20242026
most citedACON: Optimizing Context Compression for Long-horizon LLM Agents

1 citations · 1 across the 13 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs

Chanuk Lee, Minki Kang, Sung Ju Hwang

Recent studies observe that reinforcement learning with verifiable rewards (RLVR) reliably improves pass@1 on reasoning tasks, yet often fails to yield comparable gains in pass@k,…