English
Related papers

Related papers: Contrastive Reasoning Alignment: Reinforcement Lea…

200 papers

As large language models (LLMs) continue to advance in capabilities, ensuring their safety against jailbreak attacks remains a critical challenge. In this paper, we introduce a novel safety alignment approach called Answer-Then-Check, which…

Machine Learning · Computer Science 2026-03-09 Chentao Cao , Xiaojun Xu , Bo Han , Hang Li

Code agents must both reason over long-horizon repository state and obey strict tool-use protocols. In paired Instruct/Thinking checkpoints, these capabilities are complementary but misaligned. The Instruct model is concise and…

Software Engineering · Computer Science 2026-05-15 Mingzhi Zhu , Michele Merler , Raju Pavuluri , Stacy Patterson

Retrieval-Augmented Generation (RAG) faces a core bottleneck with knowledge-sparse and semantically ambiguous long-tail queries, where retrieval noise distorts reasoning and necessitates costly post-processing. To tackle this, we propose…

Artificial Intelligence · Computer Science 2025-10-28 Kaitong Cai , Jusheng Zhang , Yijia Fan , Jing Yang , Keze Wang

Despite recent progress in reinforcement learning (RL) from raw pixel data, sample inefficiency continues to present a substantial obstacle. Prior works have attempted to address this challenge by creating self-supervised auxiliary tasks,…

Machine Learning · Computer Science 2024-05-27 Ruijie Zheng , Xiyao Wang , Yanchao Sun , Shuang Ma , Jieyu Zhao , Huazhe Xu , Hal Daumé , Furong Huang

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…

Computation and Language · Computer Science 2026-02-12 Weihao Liu , Dehai Min , Lu Cheng

The aggregation of conflicting client updates remains a fundamental bottleneck in federated learning (FL) under heterogeneous data distributions. Naive averaging can produce a global update that improves the global objective while…

Machine Learning · Computer Science 2026-05-21 Ziqi Wang , Qiang Liu , Nils Thuerey

Reinforcement learning has long struggled with poor sample efficiency. One promising approach to mitigate this problem is leveraging group-invariant Markov Decision Processes ($G$-invariant MDPs). Existing works in this direction have…

Machine Learning · Computer Science 2026-05-25 Shuai Zhen , Yifan Zhang , Yuling Wang , Yanhua Yu

Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of…

Computer Vision and Pattern Recognition · Computer Science 2021-03-22 Tete Xiao , Xiaolong Wang , Alexei A. Efros , Trevor Darrell

Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a promising paradigm that organizes external knowledge into structured graphs of entities and relations, enabling large language models (LLMs) to perform complex reasoning…

Computation and Language · Computer Science 2026-04-14 Jinyoung Park , Sanghyeok Lee , Omar Zia Khan , Hyunwoo J. Kim , Joo-Kyung Kim

Recently, deep reasoning large language models(LLMs) like DeepSeek-R1 have made significant progress in tasks such as mathematics and coding. Inspired by this, several studies have employed reinforcement learning(RL) to enhance models' deep…

Computation and Language · Computer Science 2025-05-28 Zheng Li , Mao Zheng , Mingyang Song , Wenjie Yang

Deep reinforcement learning (DRL) provides a promising way for learning navigation in complex autonomous driving scenarios. However, identifying the subtle cues that can indicate drastically different outcomes remains an open problem with…

Machine Learning · Computer Science 2021-03-25 Xiaobai Ma , Jiachen Li , Mykel J. Kochenderfer , David Isele , Kikuo Fujimura

Large reasoning models often reach correct answers through flawed intermediate steps, creating a gap between final accuracy and reasoning reliability. Existing alignment strategies address this with external verifiers or massive sampling,…

Artificial Intelligence · Computer Science 2026-05-11 Kejia Chen , Jiawen Zhang , Yihong Wu , Kewei Gao , Jian Lou , Zunlei Feng , Mingli Song , Ruoxi Jia

Recommender systems increasingly incorporate textual reviews to enrich user and item representations. However, most review-aware models remain optimized for rating prediction rather than ranking quality. This misalignment limits their…

In view of its power in extracting feature representation, contrastive self-supervised learning has been successfully integrated into the practice of (deep) reinforcement learning (RL), leading to efficient policy learning in various…

Machine Learning · Computer Science 2024-04-16 Shuang Qiu , Lingxiao Wang , Chenjia Bai , Zhuoran Yang , Zhaoran Wang

Large reasoning models (LRMs) achieved remarkable performance via chain-of-thought (CoT), but recent studies showed that such enhanced reasoning capabilities are at the expense of significantly degraded safety capabilities. In this paper,…

Artificial Intelligence · Computer Science 2026-05-05 Jianan Chen , Zhifang Zhang , Shuo He , Linan Yue , Lei Feng , Minling Zhang

GRPO is a standard approach to endowing pretrained LLMs with reasoning capabilities. It estimates the advantage of an outcome from a group of $K$ outcomes, and promotes those with positive advantages inside a trust region. Since GRPO…

Machine Learning · Computer Science 2026-02-02 Wenzheng Zhang , Karl Stratos

Recent large reasoning models (LRMs) have made substantial progress in complex reasoning tasks, yet they often generate lengthy reasoning paths for every query, incurring unnecessary computation and latency. Existing speed-up approaches…

Computation and Language · Computer Science 2026-01-08 Zhaofeng Zhong , Wei Yuan , Tong Chen , Xiangyu Zhao , Quoc Viet Hung Nguyen , Hongzhi Yin

Computational learning approaches to solving visual reasoning tests, such as Raven's Progressive Matrices (RPM), critically depend on the ability to identify the visual concepts used in the test (i.e., the representation) as well as the…

Machine Learning · Computer Science 2022-07-01 Pritish Sahu , Kalliopi Basioti , Vladimir Pavlovic

The deployment of Large Reasoning Models (LRMs) in high-stakes decision-making pipelines has introduced a novel and opaque attack surface: reasoning backdoors. In these attacks, the model's intermediate Chain-of-Thought (CoT) is manipulated…

Cryptography and Security · Computer Science 2026-03-04 Zhen Guo , Shanghao Shi , Hao Li , Shamim Yazdani , Ning Zhang , Reza Tourani

Large reasoning models (LRMs) often generate long, seemingly coherent reasoning traces yet still produce incorrect answers, making hallucination detection challenging. Although trajectories contain useful signals, directly using trace text…

Machine Learning · Computer Science 2026-05-06 Jianxiong Zhang , Bing Guo , Yuming Jiang , Haobo Wang , Bo An , Sean Du