{"slug": "internreviewer-internadvocate-objective-reward-and-evaluation-for-agentic-in-and", "title": "InternReviewer & InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcement Learning in Peer Review and Rebuttal", "summary": "Researchers introduced InternReviewer and InternAdvocate, scholarly agents trained with an agentic reinforcement learning framework that uses a unified reward system to improve peer review and rebuttal generation. The framework, detailed in arXiv:2608.28612v1, incorporates a large-scale scholarly dataset and a high-efficiency arXiv retrieval tool, with multi-dimensional criteria including reference-anchored semantic alignment, structural compliance, and citation verification to eliminate hallucinations. Experimental results showed significant improvements in reasoning depth and citation accuracy.", "body_md": "arXiv:2608.28612v1 Announce Type: new\nAbstract: Generating professional scholarly content, such as peer reviews and rebuttals, requires an intricate synergy between domain reasoning and factual grounding. This work presents a comprehensive framework for the development and evaluation of specialized scholarly agents, InternReviewer and InternAdvocate. We first establish a large-scale, high-quality scholarly dataset and integrate a high-efficiency arXiv retrieval tool to enable active evidence gathering. To optimize these agents, we implement an agentic Reinforcement Learning (RL) paradigm driven by a unified objective metric and reward system. This system avoids the biases of subjective model-based judging by employing multi-dimensional criteria, including reference-anchored semantic alignment, structural compliance, and a strict verification mechanism that cross-checks citations against real-time interaction logs to eliminate hallucinations. Experimental results demonstrate that agents trained within this closed-loop framework exhibit significant improvements in reasoning depth and citation accuracy.", "url": "https://wpnews.pro/news/internreviewer-internadvocate-objective-reward-and-evaluation-for-agentic-in-and", "canonical_source": "https://arxiv.org/abs/2608.28612", "published_at": "2026-09-01 04:00:00+00:00", "updated_at": "2026-09-01 04:27:00.147916+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-research", "ai-agents"], "entities": ["InternReviewer", "InternAdvocate", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/internreviewer-internadvocate-objective-reward-and-evaluation-for-agentic-in-and", "markdown": "https://wpnews.pro/news/internreviewer-internadvocate-objective-reward-and-evaluation-for-agentic-in-and.md", "text": "https://wpnews.pro/news/internreviewer-internadvocate-objective-reward-and-evaluation-for-agentic-in-and.txt", "jsonld": "https://wpnews.pro/news/internreviewer-internadvocate-objective-reward-and-evaluation-for-agentic-in-and.jsonld"}}