Related papers: $S^3$-R1: Learning to Retrieve and Answer Step-by-…
Efficiently acquiring external knowledge and up-to-date information is essential for effective reasoning and text generation in large language models (LLMs). Prompting advanced LLMs with reasoning capabilities to use search engines during…
Can a model learn to escape its own learning plateau? Reinforcement learning methods for finetuning large reasoning models stall on datasets with low initial success rates, and thus little training signal. We investigate a fundamental…
This paper addresses two persistent challenges in sequential recommendation: (i) evidence insufficiency-cold-start sparsity together with noisy, length-varying item texts; and (ii) opaque modeling of dynamic, multi-faceted intents across…
Fine-tuning foundation models has emerged as a powerful approach for generating objects with specific desired properties. Reinforcement learning (RL) provides an effective framework for this purpose, enabling models to generate outputs that…
Existing Large Reasoning Models (LRMs) have shown the potential of reinforcement learning (RL) to enhance the complex reasoning capabilities of Large Language Models~(LLMs). While they achieve remarkable performance on challenging tasks…
Optimization problems characterized by both discrete and continuous variables are common across various disciplines, presenting unique challenges due to their complex solution landscapes and the difficulty of navigating mixed-variable…
In neural Information Retrieval, ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using efficient approximate nearest neighbors methods has proven to…
Reinforcement learning (RL) is a key post-pretraining step for aligning large language models (LLMs) with complex tasks and human preferences. While it is often assumed that RL fine-tuning requires updating most of a model's parameters, we…
Document summarisation can be formulated as a sequential decision-making problem, which can be solved by Reinforcement Learning (RL) algorithms. The predominant RL paradigm for summarisation learns a cross-input policy, which requires…
Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for self-paced RL fail in…
While modern Requirements Engineering (RE) heavily relies on natural language processing and Machine Learning (ML) techniques, their effectiveness is limited by the scarcity of high-quality datasets. This paper introduces Synthline, a…
While few-step generative models have enabled powerful image and video generation at significantly lower cost, generic reinforcement learning (RL) paradigms for few-step models remain an unsolved problem. Existing RL approaches for few-step…
In constrained reinforcement learning (RL), a learning agent seeks to not only optimize the overall reward but also satisfy the additional safety, diversity, or budget constraints. Consequently, existing constrained RL solutions require…
Model-based reinforcement learning (RL) is considered to be a promising approach to reduce the sample complexity that hinders model-free RL. However, the theoretical understanding of such methods has been rather limited. This paper…
Vision-based reinforcement learning (RL) is a promising approach to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image…
Residual reinforcement learning (RL) has been proposed as a way to solve challenging robotic tasks by adapting control actions from a conventional feedback controller to maximize a reward signal. We extend the residual formulation to learn…
Reinforcement Learning from Verifiable Rewards (RLVR) improves the reasoning abilities of Large Language Models (LLMs) but it struggles with unstable exploration. We propose FR3E (First Return, Entropy-Eliciting Explore), a structured…
Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarchical deployments with a Planner, Coordinator, and…
Vision-based reinforcement learning (RL) is a promising technique to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image…
Reinforcement Learning (RL) has recently emerged as a powerful technique for improving image and video generation in Diffusion and Flow Matching models, specifically for enhancing output quality and alignment with prompts. A critical step…