Quantile Advantage Estimation for Entropy-Safe Reasoning episode artwork

EPISODE · Sep 30, 2025 · 23 MIN

Quantile Advantage Estimation for Entropy-Safe Reasoning

from Daily Paper Cast · host Jingwen Liang, Gengyu Wang

🤗 Upvotes: 102 | cs.LG, cs.AI Authors: Junkang Wu, Kexin Huang, Jiancan Wu, An Zhang, Xiang Wang, Xiangnan He Title: Quantile Advantage Estimation for Entropy-Safe Reasoning Arxiv: http://arxiv.org/abs/2509.22611v1 Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) strengthens LLM reasoning, but training often oscillates between {entropy collapse} and {entropy explosion}. We trace both hazards to the mean baseline used in value-free RL (e.g., GRPO and DAPO), which improperly penalizes negative-advantage samples under reward outliers. We propose {Quantile Advantage Estimation} (QAE), replacing the mean with a group-wise K-quantile baseline. QAE induces a response-level, two-regime gate: on hard queries (p <= 1 - K) it reinforces rare successes, while on easy queries (p > 1 - K) it targets remaining failures. Under first-order softmax updates, we prove {two-sided entropy safety}, giving lower and upper bounds on one-step entropy change that curb explosion and prevent collapse. Empirically, this minimal modification stabilizes entropy, sparsifies credit assignment (with tuned K, roughly 80% of responses receive zero advantage), and yields sustained pass@1 gains on Qwen3-8B/14B-Base across AIME 2024/2025 and AMC 2023. These results identify {baseline design} -- rather than token-level heuristics -- as the primary mechanism for scaling RLVR.

Episode metadata supplied by the publisher feed · Published Sep 30, 2025

🤗 Upvotes: 102 | cs.LG, cs.AI Authors: Junkang Wu, Kexin Huang, Jiancan Wu, An Zhang, Xiang Wang, Xiangnan He Title: Quantile Advantage Estimation for Entropy-Safe Reasoning Arxiv: http://arxiv.org/abs/2509.22611v1 Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) strengthens LLM reasoning, but training often oscillates between {entropy collapse} and {entropy explosion}. We trace both hazards to the mean baseline used in value-free RL (e.g., GRPO and DAPO), which improperly penalizes negative-advantage samples under reward outliers. We propose {Quantile Advantage Estimation} (QAE), replacing the mean with a group-wise K-quantile baseline. QAE induces a response-level, two-regime gate: on hard queries (p <= 1 - K) it reinforces rare successes, while on easy queries (p > 1 - K) it targets remaining failures. Under first-order softmax updates, we prove {two-sided entropy safety}, giving lower and upper bounds on one-step entropy change that curb explosion and prevent collapse. Empirically, this minimal modification stabilizes entropy, sparsifies credit assignment (with tuned K, roughly 80% of responses receive zero advantage), and yields sustained pass@1 gains on Qwen3-8B/14B-Base across AIME 2024/2025 and AMC 2023. These results identify {baseline design} -- rather than token-level heuristics -- as the primary mechanism for scaling RLVR.

PodParley-generated summary based on available episode metadata and transcript content.

NOW PLAYING

Quantile Advantage Estimation for Entropy-Safe Reasoning

0:00 23:16

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

Frequently Asked Questions

How long is this episode of Daily Paper Cast?

This episode is 23 minutes long.

When was this Daily Paper Cast episode published?

This episode was published on September 30, 2025.

What is this episode about?

🤗 Upvotes: 102 | cs.LG, cs.AI Authors: Junkang Wu, Kexin Huang, Jiancan Wu, An Zhang, Xiang Wang, Xiangnan He Title: Quantile Advantage Estimation for Entropy-Safe Reasoning ...

Can I download this Daily Paper Cast episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!