Skip to content

PACT: From Credit Assignment to Critic Alignment

Sep 2026 · arXiv.org · Vol abs/2609.26355 · 0 citations · 50 references
Computer Science

TL;DR

Policy Aligned Critic Training (PACT), which adopts an Actor-then-Critic update order to apply importance sampling correction to critic training and better align the critic with the updated policy, is developed.

Abstract

Reinforcement learning has become a central component of large language model (LLM) post-training, yet token-level credit lacks a generally accepted mathematical definition, leaving its relationship to commonly used training signals unclear. We formulate three regularity conditions, namely Completeness, Prefix Consistency, and Neutrality, and prove that they uniquely determine token-level credit. This characterization provides a unified basis for explaining phenomena across existing algorithms and guides the development of an improved actor-critic training procedure. Through this lens, an ideal teacher in On-Policy Distillation (OPD) acts as an implicit critic, yielding an expected policy gradient proportional to that induced by token-level credit. Response-level REINFORCE Leave-One-Out (RLOO) signals match the expected policy-gradient contribution of token-level credit despite their coarser granularity. We further establish approximate credit sparsity under bounded outcome rewards and show how intermediate critic errors in Generalized Advantage Estimation (GAE) can become comparable to the underlying credit. These motivate Policy Aligned Critic Training (PACT), which adopts an Actor-then-Critic update order to apply importance sampling correction to critic training and better align the critic with the updated policy. In agentic mathematical reasoning, PACT achieves 72.87% average accuracy across four benchmarks, outperforming GRPO and PPO by 8.80 and 13.16 percentage points, respectively. On SWE-bench Verified, PACT achieves a pass rate of 67.4%, outperforming PPO, GRPO, and SAO by 2.4, 2.0, and 3.8 percentage points, respectively.

View source

Similar papers

Preprint Sep 2026

VERPO: Verified Evidence Regularized Policy Optimization

Verifiable rewards improve language models through reliable task-level feedback, but methods based on Group Relative Policy Optimization (GRPO) apply a sequence-level advantage uniformly across all tokens. This coarse credit assignment reinforces or penalizes entire responses without identifying which local decisions t...

Hai-Jiang Li, Cheng-Yue Lv, Yi Zhang et al. · 0 citations

UniOPSD: Unifying Outcome and Hindsight Feedback for Agentic Reinforcement Learning

UniOPSD (Unified On-Policy Self-Distillation) is introduced, which unifies these feedback sources through adaptive local credit arbitration and constructs comparable credit estimates from environmental returns and successful-peer hindsight at shared interaction anchors.

Zeng-Huang Fu, Zhao-Yang Li, Qiu-Yuan Ai et al. · 0 citations
#artificial intelligence Preprint Sep 2026

MaD-RL: Matching Distributions for Calibrating LLMs with Reinforcement Learning

This work proposes a general RL-based framework for Distribution Matching allowing matching the distribution of a latent categorical attribute of model outputs to a specified target distribution and proposes reward functions for other divergences such as KL and Jensen-Shannon and motivate them with theoretical justific...

Sourabh Kulkarni, Ksheeraj Sai Vepuri, B. Demir et al. · 1 citation

When Sparse Reward Meets Dense Distillation: Training Dynamics of On-Policy Distillation

The cross-signal NTK is introduced, a token-level statistic that measures the alignment between reward and distillation gradients at position n and an empirical threshold beyond which naive mixing can lead to persistent training collapse is revealed.

Xin-Ke Jiang, Tao Feng, Zhi-Bang Yang et al. · 1 citation

Related blog posts

MIT News · Artificial Intelligence Sep 29, 2026

Who we become when we talk to machines

Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.