Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning — Paper

Abstract

-cross Abstract: Credit assignment is a central challenge in reinforcement learning (RL). Classical actor-critic methods address this challenge through fine-grained advantage estimation based on a learned value function. However, learned value models are often avoided in modern large language model (LLM) RL because conventional discriminative critics are difficult to train reliably. We revisit value modeling and argue that this difficulty is partly due to limited expressiveness. In particular, representation complexity theory suggests that value functions can be hard to approximate under the one-shot prediction paradigm used by existing value models, and our scaling experiments show that such critics do not improve reliably with scale. Motivated by this observation, we propose Generative Actor-Critic (GenAC), which replaces one-shot scalar value prediction with a generative critic that performs chain-of-thought reasoning before producing a value estimate. We further introduce In-Context Conditioning, which helps the critic remain calibrated to the current actor throughout training. GenAC improves value approximation, ranking reliability, and out-of-distribution generalization, and these gains translate into stronger downstream RL performance than both value-based and value-free baselines. Overall, our results suggest that stronger value modeling is a promising direction for improving credit assignment in LLM reinforcement learning.

Authors 4

Zikang Shan, Han Zhong, Liwei Wang, Li Zhao

Specification

Official page: arxiv.org/abs/2604.10701
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
Arxiv announce type: replace
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
arXiv id: 2604.10701
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
Categories: cs.LG, cs.AI, cs.CL
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
PDF: arxiv.org/pdf/2604.10701
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
Primary category: cs.LG
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
Published: 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

2 h ago

Conflicts

None

No models linked to this paper yet.

Authors: Zikang Shan, Han Zhong, Liwei Wang

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · PDF

1 claims · 1 propertiesShow all properties

PDFpdf_url1

Claim history for PDF
Value	Valid from → to	Status	Source	Confidence	Extractor
https://arxiv.org/pdf/2604.10701	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
New paperPaperBringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning
New paper: Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning
arxiv
rss.arxiv.org

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.AI	feed	T1· Official	2 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.