Related papers: Learning When to Remember: Risk-Sensitive Contextu…

Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies…

We study contextual bandit (CB) problems, where the user can sometimes respond with the best action in a given context. Such an interaction arises, for example, in text prediction or autocompletion settings, where a poor suggestion is…

Mobile Context-Aware Recommender Systems can be naturally modelled as an exploration/exploitation trade-off (exr/exp) problem, where the system has to choose between maximizing its expected rewards dealing with its current knowledge…

As large language models (LLMs) are applied across diverse domains, the ability to selectively unlearn specific information is becoming increasingly essential. For instance, LLMs are expected to selectively provide confidential information…

We consider contextual linear bandits over networks, a class of sequential decision-making problems where learning occurs simultaneously across multiple locations and the reward distributions share structural similarities while also…

A recent trend in LLMs is developing recurrent sub-quadratic models that improve long-context processing efficiency. We investigate leading large long-context models, focusing on how their fixed-size recurrent memory affects their…

Large language models are making autonomous drug discovery agents increasingly feasible, but reliable success in this setting is not determined by any single action or molecule. It is determined by whether the final returned set jointly…

We consider the problem of contextual bandits and imitation learning, where the learner lacks direct knowledge of the executed action's reward. Instead, the learner can actively query an expert at each round to compare two actions and…

Long-term memory is crucial for agents in specialized web environments, where success depends on recalling interface affordances, state dynamics, workflows, and recurring failure modes. However, existing memory benchmarks for agents mostly…

Multi-agent large language model (LLM) systems have shown strong potential in complex reasoning and collaborative decision-making tasks. However, most existing coordination schemes rely on static or full-context routing strategies, which…

Cooperative multi-agent decision making involves a group of agents cooperatively solving learning problems while communicating over a network with delays. In this paper, we consider the kernelised contextual bandit problem, where the reward…

Selecting a sample generation scheme from multiple prompt-based generative models, including large language models (LLMs) and prompt-guided image and video generation models, is typically addressed by choosing the model that maximizes an…

We consider a rate-constrained contextual multi-armed bandit (RC-CMAB) problem, in which a group of agents are solving the same contextual multi-armed bandit (CMAB) problem. However, the contexts are observed by a remotely connected entity,…

Large language model (LLM) agents increasingly operate in settings where a single context window is far too small to capture what has happened, what was learned, and what should not be repeated. Memory -- the ability to persist, organize,…

Memory systems often organize user-agent interactions as retrievable external memory and are crucial for long-running agents by overcoming the limited context windows of LLMs. However, existing memory systems invoke LLMs to process every…

Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language models. However, existing RLVR methods utilize rollouts in an indiscriminate and short-horizon manner:…

Large Language Models (LLMs) increasingly use persistent memory from past interactions to enhance personalization and task performance. However, this memory introduces critical risks when sensitive information is revealed in inappropriate…

Many physical systems have underlying safety considerations that require that the strategy deployed ensures the satisfaction of a set of constraints. Further, often we have only partial information on the state of the system. We study the…

In high-stakes AI applications, even a single action can cause irreparable damage. However, nearly all of sequential decision-making theory assumes that all errors are recoverable (e.g., by bounding rewards). Standard bandit algorithms that…

We introduce a latency-aware contextual bandit framework that generalizes the standard contextual bandit problem, where the learner adaptively selects arms and switches decision sets under action delays. In this setting, the learner…