English
Related papers

Related papers: SPICE: Self-Play In Corpus Environments Improves R…

200 papers

Existing dense retrieval models struggle with reasoning-intensive retrieval task as they fail to capture implicit relevance that requires reasoning beyond surface-level semantic information. To address these challenges, we propose…

Information Retrieval · Computer Science 2025-07-18 Sangam Lee , Ryang Heo , SeongKu Kang , Dongha Lee

The dominant paradigm for improving mathematical reasoning in language models relies on Reinforcement Learning with verifiable rewards. Yet existing methods treat each problem instance in isolation without leveraging the reusable strategies…

Artificial Intelligence · Computer Science 2026-03-20 Yu Li , Rui Miao , Zhengling Qi , Tian Lan

Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly learn relevant knowledge from the given context. An intuitive…

In scenarios where language models must incorporate new information efficiently without extensive retraining, traditional fine-tuning methods are prone to overfitting, degraded generalization, and unnatural language generation. To address…

Computation and Language · Computer Science 2025-04-01 Siyuan Qi , Bangcheng Yang , Kailin Jiang , Xiaobo Wang , Jiaqi Li , Yifan Zhong , Yaodong Yang , Zilong Zheng

Reinforcement learning (RL) has proven effective for fine-tuning large language models (LLMs), significantly enhancing their reasoning abilities in domains such as mathematics and code generation. A crucial factor influencing RL fine-tuning…

Artificial Intelligence · Computer Science 2025-10-31 Xiaoyin Chen , Jiarui Lu , Minsu Kim , Dinghuai Zhang , Jian Tang , Alexandre Piché , Nicolas Gontier , Yoshua Bengio , Ehsan Kamalloo

An important challenge in reinforcement learning is training agents that can solve a wide variety of tasks. If tasks depend on each other (e.g. needing to learn to walk before learning to run), curriculum learning can speed up learning by…

Recent advancements in long-context large language models have attracted significant attention, yet their practical applications often suffer from suboptimal context utilization. This study investigates structuring training data to enhance…

Computation and Language · Computer Science 2025-03-03 Konrad Staniszewski , Szymon Tworkowski , Sebastian Jaszczur , Yu Zhao , Henryk Michalewski , Łukasz Kuciński , Piotr Miłoś

Text corpus exploration (TCE) spans the range of exploratory search tasks: it goes beyond simple retrieval to include item discovery and learning about the corpus and topic. Systems support TCE with tools such as similarity-based…

Human-Computer Interaction · Computer Science 2024-06-17 Michael Gleicher , Keaton Leppenan , Yunyu Bai

Reinforcement learning has advanced video reasoning in large multi-modal models, yet dominant pipelines either rely on on-policy self-exploration, which plateaus at the model's knowledge boundary, or hybrid replay that mixes policies and…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Haojian Huang , Chuanyu Qin , Yinchuan Li , Yingcong Chen

Deploying language-model agents in production often requires substantial compute and human effort to tune prompts, parsers, validators, and other components of the agent pipeline. Self-evolution offers a promising alternative, but most…

Machine Learning · Computer Science 2026-05-25 Chen Ling , Pei Chen , Albert Guan , Jiaming Qu , Shayan Ali Akbar , Madhu Gopinathan , Erwin Cornejo

Robot learning has proven to be a general and effective technique for programming manipulators. Imitation learning is able to teach robots solely from human demonstrations but is bottlenecked by the capabilities of the demonstrations.…

Robotics · Computer Science 2024-10-24 Zihan Zhou , Animesh Garg , Dieter Fox , Caelan Garrett , Ajay Mandlekar

Prompt-based models have demonstrated impressive prompt-following capability at image editing tasks. However, the models still struggle with following detailed editing prompts or performing local edits. Specifically, global image quality…

Graphics · Computer Science 2025-10-20 Kenan Tang , Yanhong Li , Yao Qin

Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the…

Computation and Language · Computer Science 2023-12-25 Afra Amini , Massimiliano Ciaramita

This work investigates the reasoning and planning capabilities of foundation models and their scalability in complex, dynamic environments. We introduce PuzzlePlex, a benchmark designed to assess these capabilities through a diverse set of…

Artificial Intelligence · Computer Science 2025-10-09 Yitao Long , Yuru Jiang , Hongjun Liu , Yilun Zhao , Jingchen Sun , Yiqiu Shen , Chen Zhao , Arman Cohan , Dennis Shasha

Reinforcement learning is a widely used approach to autonomous navigation, showing potential in various tasks and robotic setups. Still, it often struggles to reach distant goals when safety constraints are imposed (e.g., the wheeled robot…

Robotics · Computer Science 2024-08-27 Brian Angulo , Gregory Gorbov , Aleksandr Panov , Konstantin Yakovlev

High-quality labeled datasets are crucial for training and evaluating foundation models in software engineering, but creating them is often prohibitively expensive and labor-intensive. We introduce SPICE, a scalable, automated pipeline for…

Understanding and reasoning about physics is an important ability of intelligent agents. We develop the PHYRE benchmark for physical reasoning that contains a set of simple classical mechanics puzzles in a 2D physical environment. The…

Machine Learning · Computer Science 2019-08-16 Anton Bakhtin , Laurens van der Maaten , Justin Johnson , Laura Gustafson , Ross Girshick

Self-play with large language models has emerged as a promising paradigm for achieving self-improving artificial intelligence. However, existing self-play frameworks often suffer from optimization instability, due to (i) non-stationary…

Artificial Intelligence · Computer Science 2026-01-22 Shengda Fan , Xuyan Ye , Yankai Lin

This work-in-progress paper presents SPARC (Systematic Problem Solving and Algorithmic Reasoning for Children), a gamified learning platform designed to enhance engagement and knowledge retention in K-12 STEM education. Traditional…

Computers and Society · Computer Science 2025-08-05 Chengzhang Zhu , Cecile H. Sam , Yanlai Wu , Ying Tang

Throughout long history, natural species have learned to survive by evolving their physical structures adaptive to the environment changes. In contrast, current reinforcement learning (RL) studies mainly focus on training an agent with a…

Artificial Intelligence · Computer Science 2023-09-25 Shuang Ao , Tianyi Zhou , Guodong Long , Xuan Song , Jing Jiang