Shengyu Feng

Yun He, Wenzhe Li, Hejia Zhang et al.

Recent progress in large language models (LLMs) has led to impressive performance on a range of tasks, yet advanced instruction following (IF)-especially for complex, multi-turn, and system-prompted instructions-remains a significant challenge. Rigorous evaluation and effective training for such capabilities are hindered by the lack of high-quality, human-annotated benchmarks and reliable, interpretable reward signals. In this work, we introduce AdvancedIF (we will release this benchmark soon), a comprehensive benchmark featuring over 1,600 prompts and expert-curated rubrics that assess LLMs ability to follow complex, multi-turn, and system-level instructions. We further propose RIFL (Rubric-based Instruction-Following Learning), a novel post-training pipeline that leverages rubric generation, a finetuned rubric verifier, and reward shaping to enable effective reinforcement learning for instruction following. Extensive experiments demonstrate that RIFL substantially improves the instruction-following abilities of LLMs, achieving a 6.7% absolute gain on AdvancedIF and strong results on public benchmarks. Our ablation studies confirm the effectiveness of each component in RIFL. This work establishes rubrics as a powerful tool for both training and evaluating advanced IF in LLMs, paving the way for more capable and reliable AI systems.

Shengyu Feng, Yiming Yang

Mixed Integer Linear Program (MILP) solvers are mostly built upon a Branch-and-Bound (B\&B) algorithm, where the efficiency of traditional solvers heavily depends on hand-crafted heuristics for branching. The past few years have witnessed the increasing popularity of data-driven approaches to automatically learn these heuristics. However, the success of these methods is highly dependent on the availability of high-quality demonstrations, which requires either the development of near-optimal heuristics or a time-consuming sampling process. This paper averts this challenge by proposing Suboptimal-Demonstration-Guided Reinforcement Learning (SORREL) for learning to branch. SORREL selectively learns from suboptimal demonstrations based on value estimation. It utilizes suboptimal demonstrations through both offline reinforcement learning on the demonstrations generated by suboptimal heuristics and self-imitation learning on past good experiences sampled by itself. Our experiments demonstrate its advanced performance in both branching quality and training efficiency over previous methods for various MILPs.

Shengyu Feng, Yun He, Shuang Ma et al.

Reinforcement learning (RL) has recently proven effective at scaling chain-of-thought (CoT) reasoning in large language models on tasks with verifiable answers. However, extending RL to more general non-verifiable tasks, typically in the format of human preference pairs, remains both challenging and underexplored. In this work, we propose Dual-Weighted Reinforcement Learning (DWRL), a new framework for preference modeling that integrates CoT reasoning with the Bradley-Terry (BT) model via a dual-weighted RL objective that preserves preference-modeling inductive bias. DWRL approximates the maximum-likelihood objective of the BT model with two complementary weights: an instance-wise misalignment weight, which emphasizes under-trained pairs misaligned with human preference, and a group-wise (self-normalized) conditional preference score, which promotes promising thoughts. In this paper, we apply DWRL to preference modeling by training generative preference models (GPMs) to first generate a thought and then predict the human preference score. Across multiple benchmarks and model scales (Llama3 and Qwen2.5), DWRL consistently outperforms both GPM baselines and scalar models, while producing coherent, interpretable thoughts. In summary, our results position DWRL as a general framework for reasoning-enhanced preference learning beyond verifiable tasks.

Yijie Guo, Jongwook Choi, Marcin Moczulski et al.

Reinforcement learning with sparse rewards is challenging because an agent can rarely obtain non-zero rewards and hence, gradient-based optimization of parameterized policies can be incremental and slow. Recent work demonstrated that using a memory buffer of previous successful trajectories can result in more effective policies. However, existing methods may overly exploit past successful experiences, which can encourage the agent to adopt sub-optimal and myopic behaviors. In this work, instead of focusing on good experiences with limited diversity, we propose to learn a trajectory-conditioned policy to follow and expand diverse past trajectories from a memory buffer. Our method allows the agent to reach diverse regions in the state space and improve upon the past trajectories to reach new states. We empirically show that our approach significantly outperforms count-based exploration methods (parametric approach) and self-imitation learning (parametric approach with non-parametric memory) on various complex tasks with local optima. In particular, without using expert demonstrations or resetting to arbitrary states, we achieve the state-of-the-art scores under five billion number of frames, on challenging Atari games such as Montezuma's Revenge and Pitfall.