# PIR: Teach Reasoning Models to Ask Proactively and Bid Farewell to Blind Self-Thinking

> PIR (Proactive Interactive Reasoning) is a new paradigm that transforms reasoning models from passive solvers into active inquirers through uncertainty detection and reinforcement learning, significantly reducing over-reasoning and hallucination issues.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-05-27T10:01:07.000Z
- 最近活动: 2026-05-27T10:20:50.943Z
- 热度: 139.7
- 关键词: 推理模型, 主动学习, 强化学习, 人机交互, 不确定性检测, GRPO, ACL 2026
- 页面链接: https://www.zingnex.cn/en/forum/thread/pir
- Canonical: https://www.zingnex.cn/forum/thread/pir
- Markdown 来源: floors_fallback

---

## 【Introduction】PIR: A New Paradigm for Turning Reasoning Models from Passive Solvers to Active Inquirers

PIR (Proactive Interactive Reasoning) is a new paradigm that transforms reasoning models from passive solvers into active inquirers through uncertainty detection and reinforcement learning, significantly reducing over-reasoning and hallucination issues.

The original authors are the Chen-X666 team (Xin Chen, Feng Jiang, Yiqian Zhang, etc.), the project was released in May 2026, the paper was accepted by ACL 2026 (arXiv:2601.22139), GitHub link: https://github.com/Chen-X666/Proactive-Interactive-R1.

## Background: The Dilemma of 'Blind Self-Thinking' in Reasoning Models

Current mainstream reasoning models (such as GPT-o1, DeepSeek-R1) have significant flaws when facing complex problems: even if key information is missing or user intent is ambiguous, they still continue internal reasoning, eventually leading to overthinking, hallucinations, or conclusions that do not match user needs. This phenomenon is called 'blind self-thinking'.

Analogy: A student who, when encountering an unfamiliar question in an exam, writes randomly based on feeling instead of asking for clarification.

## Core Methods of PIR: Two Stages of Proactive Interactive Reasoning

The PIR framework forms a 'think-ask-respond' loop through two stages:
1. **Interaction Capability Activation**: Use prediction entropy to detect uncertainty in reasoning; when the entropy value exceeds a threshold, actively ask questions. Train the model to learn when to ask through supervised fine-tuning (SFT);
2. **User Intent Alignment**: Introduce the US-GRPO (User Simulator-augmented Group Relative Policy Optimization) algorithm, where the reward function considers three dimensions: output accuracy, reasoning efficiency, and question usefulness.

## Experimental Evidence: PIR Brings Significant Performance Improvements

The paper reports that PIR performs excellently in multiple benchmark tests:
- Accuracy increased by 32.70%;
- Pass rate increased by 22.90%;
- BLEU score increased by 41.36;
- Reasoning tokens and interaction rounds reduced by nearly half.

It not only improves performance but also reduces computational costs and interaction burdens.

## Technical Implementation and Usage Guide

The project is based on the LLaMA-Factory, verl, and verl-tool frameworks. The training process has two steps:
1. Cold-start SFT: Fine-tune the base model using 'reasoning-asking' data;
2. US-GRPO Reinforcement Learning: Optimize the strategy in a user simulator environment.

Pre-trained models (such as Proactive-Interactive-R1-Math-7B) are available for download from Hugging Face, supporting vLLM deployment for interactive demos.

## Significance and Outlook: Redefining the Human-Machine Interaction Paradigm

PIR redefines human-machine interaction: from one-way user question → model answer to two-way dialogue, where the model actively clarifies needs, similar to how human experts ask for details.

Applicable fields expand to mathematical reasoning, code generation, medical diagnosis, legal consultation, etc. In the future, more intelligent assistants that ask proactively are expected to emerge, bidding farewell to blind guessing.