Related papers: PolicyLong: Towards On-Policy Context Extension

We study off-policy evaluation and learning from sequential data in a structured class of Markov decision processes that arise from repeated interactions with an exogenous sequence of arrivals with contexts, which generate unknown…

LLM agents operating under organizational policies must comply with authorization constraints typically specified in natural language. In practice, such specifications inevitably contain ambiguities and logical or semantic gaps that cause…

Large language models (LLMs) have advanced in large strides due to the effectiveness of the self-attention mechanism that processes and compares all tokens at once. However, this mechanism comes with a fundamental issue -- the predetermined…

Reinforcement learning (RL) has been extensively employed in a wide range of decision-making problems, such as games and robotics. Recently, diffusion policies have shown strong potential in modeling multi-modal behaviors, enabling more…

The deployment of Large Language Models (LLMs) in long-context scenarios is hindered by computational inefficiency and significant information redundancy. Although recent advancements have widely adopted context compression to address these…

Recently, foundation models such as OpenAI's O1 and O3, along with DeepSeek's R1, have demonstrated strong reasoning capacities and problem-solving skills acquired through large-scale reinforcement learning (RL), with wide applications in…

Large Language Models (LLMs) have demonstrated impressive capabilities across a range of natural language processing tasks. In particular, improvements in reasoning abilities and the expansion of context windows have opened new avenues for…

In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient. On-policy methods typically generate reliable policy improvement throughout training, while…

The advent of Large Language Models (LLMs) represents a notable breakthrough in Natural Language Processing (NLP), contributing to substantial progress in both text comprehension and generation. However, amidst these advancements, it is…

Social goods, such as healthcare, smart city, and information networks, often produce ordered event data in continuous time. The generative processes of these event data can be very complex, requiring flexible models to capture their…

Reinforcement learning (RL) policies are typically trained for fixed objectives, making reuse difficult when task requirements change. We study inference-time policy reuse: given a library of pre-trained policies and a new composite…

Recent advancements in proactive dialogues have garnered significant attention, particularly for more complex objectives (e.g. emotion support and persuasion). Unlike traditional task-oriented dialogues, proactive dialogues demand advanced…

The rapid development of large language models (LLMs) is reshaping operational paradigms across multidisciplinary domains. LLMs' emergent capability to synthesize policy-relevant insights across disciplinary boundaries suggests potential as…

Due to limited resources and public safety concerns, deep reinforcement learning (RL) agents for many cyber-physical systems (e.g., autonomous vehicles) are first trained in simulators. However, when deployed in real world environments,…

Solving complex or long-horizon problems often requires large language models (LLMs) to use external tools and operate over a significantly longer context window. New LLMs enable longer context windows and support tool calling capabilities.…

Conventional reinforcement learning (RL) needs an environment to collect fresh data, which is impractical when online interactions are costly. Offline RL provides an alternative solution by directly learning from the previously collected…

Reinforcement learning (RL) has been effective for post-training autoregressive (AR) language models, but extending these methods to diffusion language models (DLMs) is challenging due to intractable sequence-level likelihoods. Existing…

LongRoPE2 is a novel approach that extends the effective context window of pre-trained large language models (LLMs) to the target length, while preserving the performance on the original shorter context window. This is achieved by three…

As multiple crises threaten the sustainability of our societies and pose at risk the planetary boundaries, complex challenges require timely, updated, and usable information. Natural-language processing (NLP) tools enhance and expand data…

The challenge in the widely applicable online matching problem lies in making irrevocable assignments while there is uncertainty about future inputs. Most theoretically-grounded policies are myopic or greedy in nature. In real-world…