Related papers: Recoverability Has a Law: The ERR Measure for Tool…

Large Language Models (LLMs) often struggle with mathematical reasoning tasks requiring precise, verifiable computation. While Reinforcement Learning (RL) from outcome-based rewards enhances text-based reasoning, understanding how agents…

Conversational agents powered by large language models (LLMs) with tool integration achieve strong performance on fixed task-oriented dialogue datasets but remain vulnerable to unanticipated, user-induced errors. Rather than focusing on…

Natural language instruction following is paramount to enable collaboration between artificial agents and human beings. Natural language-conditioned reinforcement learning (RL) agents have shown how natural languages' properties, such as…

Operating under real world conditions is challenging due to the possibility of a wide range of failures induced by execution errors and state uncertainty. In relatively benign settings, such failures can be overcome by retrying or executing…

Deploying small language models (7-9B parameters) as autonomous agents requires trust in their reasoning, not just their outputs. We reveal a critical reliability crisis: 50-69\% of correct answers from these models contain fundamentally…

Empirical risk minimization (ERM) is the workhorse of machine learning, whether for classification and regression or for off-policy policy learning, but its model-agnostic guarantees can fail when we use adaptively collected data, such as…

Explanation regularisation (ER) has been introduced as a way to guide text classifiers to form their predictions relying on input tokens that humans consider plausible. This is achieved by introducing an auxiliary explanation loss that…

Speculative Decoding is a prominent technique for accelerating the autoregressive inference of large language models (LLMs) by employing a fast draft model to propose candidate token sequences and a large target model to verify them in…

Persistent language-model agents increasingly combine tool use, tiered memory, reflective prompting, and runtime adaptation. In such systems, behavior is shaped not only by current prompts but by mutable internal conditions that influence…

What data or environments to use for training to improve downstream performance is a longstanding and very topical question in reinforcement learning. In particular, Unsupervised Environment Design (UED) methods have gained recent attention…

We study the problem of guaranteeing low regret in repeated games against an opponent with unknown membership in one of several classes. We add the constraint that our algorithm is non-exploitable, in that the opponent lacks an incentive to…

Customers of machine learning systems demand accountability from the companies employing these algorithms for various prediction tasks. Accountability requires understanding of system limit and condition of erroneous predictions, as…

Deep reinforcement learning has achieved impressive successes yet often requires a very large amount of interaction data. This result is perhaps unsurprising, as using complicated function approximation often requires more data to fit, and…

Finetuning language models with reinforcement learning (RL), e.g. from human feedback (HF), is a prominent method for alignment. But optimizing against a reward model can improve on reward while degrading performance in other areas, a…

In this work we provide provable regret guarantees for an online meta-learning control algorithm in an iterative control setting, where in each iteration the system to be controlled is a linear deterministic system that is different and…

As predictive models are increasingly being deployed in high-stakes decision making (e.g., loan approvals), there has been growing interest in post hoc techniques which provide recourse to affected individuals. These techniques generate…

Tool-calling agents are evaluated on tool selection, parameter accuracy, and scope recognition, yet LLM trajectory assessments remain inherently post-hoc. Disconnected from the active execution loop, such assessments identify errors that…

In settings where Machine Learning (ML) algorithms automate or inform consequential decisions about people, individual decision subjects are often incentivized to strategically modify their observable attributes to receive more favorable…

Achieving sample efficiency in online episodic reinforcement learning (RL) requires optimally balancing exploration and exploitation. When it comes to a finite-horizon episodic Markov decision process with $S$ states, $A$ actions and…

In online inverse linear optimization, a learner observes time-varying sets of feasible actions and an agent's optimal actions, selected by solving linear optimization over the feasible actions. The learner sequentially makes predictions of…