Related papers: Self-Correction as Feedback Control: Error Dynamic…
Large Language Models (LLMs) often exhibit strong linguistic abilities while remaining unreliable on multi-step reasoning tasks, particularly when deployed without additional training or fine-tuning. In this work, we study inference-time…
Feedback optimization is a control paradigm that enables physical systems to autonomously reach efficient operating points. Its central idea is to interconnect optimization iterations in closed-loop with the physical plant. Since iterative…
There has been considerable divergence of opinion on the reasoning abilities of Large Language Models (LLMs). While the initial optimism that reasoning might emerge automatically with scale has been tempered thanks to a slew of…
In the online non-stochastic control problem, an agent sequentially selects control inputs for a linear dynamical system when facing unknown and adversarially selected convex costs and disturbances. A common metric for evaluating control…
Language models increasingly show their work by writing step-by-step reasoning before answering. But are these steps genuinely used, or is the answer rigid - fixed before reasoning begins? We introduce the Step-Level Reasoning Capacity…
Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge. Despite substantial progress in benchmarking CL methods, comparative evaluations typically keep the fine-tuning regime…
Imitation learning (IL) and reinforcement learning (RL) each offer distinct advantages for robotics policy learning: IL provides stable learning from demonstrations, and RL promotes generalization through exploration. While existing robot…
As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes critical. A vital risk is intrinsic deception, wherein models strategically mislead users to achieve their own objectives. Existing…
The stability of recursively trained large language models (LLMs) is a foundational problem for AI safety. Prevailing theory predicts model collapse, a progressive degradation when models are trained on their own output. We challenge this…
Model-free approaches for reinforcement learning (RL) and continuous control find policies based only on past states and rewards, without fitting a model of the system dynamics. They are appealing as they are general purpose and easy to…
Large language models (LLMs) have revolutionized natural language processing with their ability to generate coherent and contextually relevant text. However, their deployment raises significant concerns about the potential for generating…
We consider the problem of adaptive control of a class of feedback linearizable plants with matched parametric uncertainties whose states are accessible, subject to state constraints, which often arise due to safety considerations. In this…
Large language model (LLM) agents are increasingly used to migrate legacy code to modern stacks. We ask a deceptively simple question: when an LLM modernizes legacy code, can the same model be relied upon to recognize when its own output…
The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, mining valid supervision faces three challenges: (1) Label…
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…
Although large language models (LLMs) have demonstrated remarkable reasoning capabilities, they still face challenges in knowledge-intensive multi-hop reasoning. Recent work explores iterative retrieval to address complex problems. However,…
In data-driven control design, an important problem is to deal with uncertainty due to limited and noisy data. One way to do this is to use a min-max approach, which aims to minimize some design criteria for the worst-case scenario.…
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…
The rapid electrification and intelligence of modern transportation systems place stringent demands on the electromagnetic compatibility, reliability, and adaptability of automotive power electronics. In electric and autonomous vehicles,…
Large Language Models (LLMs) have demonstrated the capability to refine their generated answers through self-correction, enabling continuous performance improvement over multiple rounds. However, the mechanisms underlying how and why…