# PACE: Phase-Progress-Aware Credit for Long-Horizon Embodied Manipulation

arXiv: https://arxiv.org/abs/2608.15026 · HTML: https://mlsanity.com/paper/2608.15026/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning and chain-of-thought in VLA, one of 13 directions in Vision-language-action models.
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 15 Aug 2026.

## Placed in

- Vision-language-action models / [Reasoning and chain-of-thought in VLA](https://mlsanity.com/vla/reasoning-and-chain-of-thought-in-vla/)

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [A Distributional Perspective on Reinforcement Learning](https://mlsanity.com/paper/1707.06887/) (2017)
- [π*0.6: a VLA That Learns From Experience](https://mlsanity.com/paper/2511.14759/) (2025)
- [VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning](https://mlsanity.com/paper/2505.18719/) (2025)
- [ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy](https://mlsanity.com/paper/2502.05450/) (2025)
- [Vision Language Models are In-Context Value Learners](https://mlsanity.com/paper/2411.04549/) (2024)
- [Diffusion Guidance Is a Controllable Policy Improvement Operator](https://mlsanity.com/paper/2505.23458/) (2025)
- [TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization](https://mlsanity.com/paper/2506.08440/) (2025)
- [Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution](https://mlsanity.com/paper/2602.12684/) (2026)
- [SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation](https://mlsanity.com/paper/2509.25358/) (2025)
- [ARM: Advantage Reward Modeling for Long-Horizon Manipulation](https://mlsanity.com/paper/2604.03037/) (2026)
- [IG-RFT: An Interaction-Guided RL Framework for VLA Models in Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2602.20715/) (2026)
- [ProgVLA: Progress-Aware Robot Manipulation Skill Learning](https://mlsanity.com/paper/2605.28231/) (2026)
- [Bi-HIL: Bilateral Control-Based Multimodal Hierarchical Imitation Learning via Subtask-Level Progress Rate and Keyframe Memory for Long-Horizon Contact-Rich Robotic Manipulation](https://mlsanity.com/paper/2603.13315/) (2026)

## Built on by (most cited first, 1 of 1)

- [PRICE the Action Chunks: Physical Relational Credit Assignment for Embodied Reinforcement Learning](https://mlsanity.com/paper/2609.38890/) (2026)

## Abstract (arXiv)

Post-training of vision-language-action (VLA) models typically relies on expert demonstrations and policy interaction trajectories. However, in long-horizon manipulation, a single episode often spans hundreds of control steps and multiple phases, while success or failure is only revealed at episode termination. Policy improvement therefore requires step-level credit signals to distinguish behaviors that advance the task from those that stall or regress. We present PACE, a credit-assignment framework for post-training on long-horizon manipulation, centered on a phase-progress-aware critic. PACE consists of two key modules: (1) the Global-Local Cooperative Value-Correction Critic (GLC-Critic) aggregates visual and motion-difference features within local temporal windows to infer the phase and intra-phase progress of each step, and applies residual correction to a discretized remaining-cost distribution accordingly, enabling step-level credit assignment; (2) Progressive Policy Distillation (PPD) converts credit into positive and negative conditions via task-wise thresholds and trains a credit-conditioned action generation policy: it first protects the pretrained policy with high-credit positive samples, then incorporates all positive and negative credits to learn the quality boundary, and at inference amplifies high-credit behaviors through the difference between conditional outputs. Extensive simulation experiments and diverse real-world robotic-arm experiments demonstrate that PACE consistently achieves significant improvements over the strongest baseline.