arXiv:2607. 26358v1 Announce Type: new Abstract: Reinforcement learning (RL) fine-tuning is widely used in language model training to improve model performance on a target task while limiting drift from a reference policy.
By Keegan Harris, Brian W. Lee, Ian Waudby-Smith, Philip Amortila, Nika Haghtalab, Michael I. Jordan
Reinforcement learning (RL) fine-tuning is widely used in language model training to improve model performance on a target task while limiting drift from a reference policy. A standard way to balance this trade-off is via a KL-regularized RL objective, although this formulation does not by itself provide a principled way to set the regularization coefficient.
arXiv:2605.10981v2 Announce Type: replace-cross
Abstract: Reference-free preference optimization has emerged as an efficient alternative to reinforcement learning from human feedback, with Simple Pre...
By Zhengyuan Fan, Zhonghua Wu, Yuxuan Du, Qun Chen
arXiv:2608. 06825v1 Announce Type: new Abstract: Learning from correct demonstrations is harder than supervised learning when many answers are correct: after predicting, the learner sees one valid answer but not whether its own answer was valid, nor any reward.
By Pahan Dewasurendra
The paper investigates preference-based bandits where a learner selects pairs of arms and receives binary preference feedback modeled by Bradley–Terry. It introduces the locally sensitive eluder dimension, a new complexity measure for logistic preference feedback, and proposes the GINOP algorithm that uses log-loss confidence sets to balance optimism and exploration. The authors prove a first-order regret bound showing that learning with preference feedback can be as statistically efficient as learning from direct rewards, and they validate their theory with empirical experiments.
By Ahmed Ben Yahmed (CREST, ENSAE Paris, FAIRPLAY), Marc Abeille (FAIRPLAY), Cl\'ement Calauz\`enes (FAIRPLAY)
arXiv:2607. 16240v1 Announce Type: cross Abstract: Direct Alignment Algorithms (DAAs) such as DPO have become a common way to post-train and align LLMs with human preferences.
By Shawn Im, Federico Danieli, Skyler Seto, Barry-John Theobald, Katherine Metcalf
The paper introduces an Onsager‑corrected, target‑policy‑weighted criterion that estimates the out‑of‑sample risk of a reward model trained on the full dataset using only its training data, thereby eliminating the need for sample splitting. This approach allows early stopping along a full‑data gradient‑descent trajectory and provides uniform consistency guarantees for neural networks under Gaussian contexts and single‑index rewards. The correction also yields a doubly robust policy‑value estimator that remains consistent even when reward‑model prediction error does not vanish, and experiments demonstrate reduced risk‑estimation error and improved reward‑model selection compared to held‑out baselines.
whyItMatters":"By removing the need for sample splitting, the method enables more efficient use of data and improves the reliability of off‑policy evaluation and reward‑model selection in high‑dimensional settings."
By Saksham Jain, Guillaume Braun, Masaaki Imaizumi
arXiv:2605. 00762v2 Announce Type: replace Abstract: We study meritocratic fairness in budgeted combinatorial multi-armed bandits with full-bandit feedback, where a learner selects at most $K$ arms per time step and observes only the noisy aggregate reward of the selected set.
By Shradha Sharma, Shweta Jain, Swapnil Dhamal
arXiv:2606. 01081v1 Announce Type: new Abstract: Decision-focused learning (DFL) trains predictive models by optimizing downstream decision quality rather than standalone prediction accuracy.
By Wyame Benslimane, Tinghan Ye, Pascal Van Hentenryck, Paul Grigas
arXiv:2609.36945v1 Announce Type: new
Abstract: We study the learning dynamics of fine-tuning a policy model on self-generated and reward-weighted data, with particular focus on a generalized version...
By Zhiwei Wang, Yanxi Chen, Yaliang Li, Bolin Ding
arXiv:2609.38860v1 Announce Type: cross
Abstract: Learning from human preferences is central to large language model (LLM) alignment, but human preference annotation is costly. Active preference lear...
By Zhongman Du, Huiming Zhang, Haodong Zhu, Baochang Zhang
arXiv:2608. 16072v1 Announce Type: cross Abstract: Reinforcement learning (RL) with group-relative advantages has become the de facto standard for post-training language model reasoners.
By Yixuan Wang, Yifei Chen, Haichao Zhang, Haozheng Luo, Xander Wu, Jie Ni, Yun Fu, Nuno Vasconcelos, Yijiang Li