AMARIS: A Memory-Augmented Rubric Improvement System for Rubric-Based Reinforcement Learning
Rubric-based reward shaping provides interpretable and editable reward signals for fine-tuning LLMs via reinforcement learning (RL), but existing adaptive rubric methods typically update criteria from local evidence such as the current batch or instance-level comparisons. This local view discards diagnostic information produced during training, making it difficult to track recurring failures, evaluate previous rubric edits, or raise standards once earlier criteria become saturated. We introduce AMARIS, A Memory-Augmented Rubric Improvement System that grounds rubric updates in longitudinal training evidence. AMARIS stores rollout analyses, step-level summaries, and rubric update records in a persistent evaluation memory, then retrieves recent and semantically relevant history to revise rubrics. We evaluate AMARIS across science, medicine, instruction following, and creative writing under both global and instance-specific rubric settings. AMARIS improves over static, local-adaptive, and memory-ablated baselines, such as +2.8 points on GPQA-Diamond and +2.2 points on IFBench over the strongest baselines, while analysis shows that memory reduces oscillatory rubric edits and supports a progression from early failure correction to later curriculum advancement. AMARIS runs asynchronously alongside the normal RL loop, reducing blocking latency relative to synchronous rubric updates.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningInstruction FollowingSimilar Papers 제목 키워드 기반
Distilling Feedback into Memory-as-a-Tool
We propose a framework that amortizes the cost of inference-time reasoning by converting transient critiques into retrievable guidelines, through a file-based memory system and agent-controlled tool calls. We evaluate th…
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
Training deep research agents, namely systems that plan, search, evaluate evidence, and synthesize long-form reports, pushes reinforcement learning beyond the regime of verifiable rewards. Their outputs lack ground-truth…
Reinforcement LearningC2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences
Rubric-augmented verification guides reward models with explicit evaluation criteria, yielding more reliable judgments than single-model verification. However, most existing methods require costly rubric annotations, lim…
Retrieval-Augmented Agentic Rubric Generation for Reliable Medical Response Evaluation
Large Language Models (LLMs) are increasingly used for clinical decision support, where hallucinations and unsafe suggestions may pose direct risks to patient safety. These risks are hard to assess: subtle clinical error…
SibylSense: Adaptive Rubric Learning via Memory Tuning and Adversarial Probing
Designing aligned and robust rewards for open-ended generation remains a key barrier to RL post-training. Rubrics provide structured, interpretable supervision, but scaling rubric construction is difficult: expert rubric…