paper-with-me

Papers

SibylSense: Adaptive Rubric Learning via Memory Tuning and Adversarial Probing

2026-02-24 · Yifei Xu, Guilherme Potje, Shivam Shandilya, Tiancheng Yuan, Leonardo de Oliveira Nunes, Rakshanda Agarwal, Saeid Asgari, Adam Atkinson, Emre Kıcıman, Songwu Lu, Ranveer Chandra, Tusher Chakraborty arxiv

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 rubrics are costly, prompted rubrics are often superficial or inconsistent, and fixed-pool discriminative rubrics can saturate and drift, enabling reward hacking. We present SibylSense, an inference-time learning approach that adapts a frozen rubric generator through a tunable memory bank of validated rubric items. Memory is updated via verifier-based item rewards measured by reference-candidate answer discriminative gaps from a handful of examples. SibylSense alternates memory tuning with a rubric-adversarial policy update that produces rubric-satisfying candidate answers, shrinking discriminative gaps and driving the rubric generator to capture new quality dimensions. Experiments on two open-ended tasks show that SibylSense yields more discriminative rubrics and improves downstream RL performance over static and non-adaptive baselines.

📄 PDF Abstract BibTeX arXiv:2602.20751

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AMARIS: A Memory-Augmented Rubric Improvement System for Rubric-Based Reinforcement Learning

2026-05-18 · Peilin Wu, Xinlu Zhang, Kun Wan, Wentian Zhao 외 arxiv

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…

Reinforcement LearningInstruction Following

Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory

2021-02-02 · ZhiYu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis

We consider the problem of tracking an adversarial state sequence in a linear dynamical system subject to adversarial disturbances and loss functions, generalizing earlier settings in the literature. To this end, we deve…

APTER: Adaptive Post-Training with Expert-Grounded Rubrics

2026-08-14 · Xukai Wang, Liangqi Li, Zhiyue Xu, Jingang Zhou 외 arxiv

As large language models enter professional domains, they must satisfy domain constraints, include critical evidence, and provide complete reasoning rather than merely produce fluent responses. Existing post-training met…

Mathematical ReasoningReinforcement LearningQuestion Answering

Fuzzy, Symbolic, and Contextual: Enhancing LLM Instruction via Cognitive Scaffolding

2025-08-28 · Vanessa Figueiredo arxiv

We study how prompt-level inductive biases influence the cognitive behavior of large language models (LLMs) in instructional dialogue. We introduce a symbolic scaffolding method paired with a short-term memory schema des…

ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents

2026-06-02 · Zheng Liu, Longxiang Zhang, Xintong Wang, Zhiang Xu 외 arxiv

LLM-based search agents are trained predominantly with outcome-only reward, leaving the search process itself unsupervised. This signal degenerates on outcome-homogeneous groups where all sampled trajectories share the s…