Related papers: Self-Correction as Feedback Control: Error Dynamic…

Subjective evaluation of LLM behavior -- empathy, restraint, calibrated emotional tone -- is hard. Human inter-rater agreement on such qualities saturates near rho ~ 0.45, and an LLM-as-judge proxy alone risks circularity: a judge sharing…

A central piece in enabling intelligent agentic behavior in foundation models is to make them capable of introspecting upon their behavior, reasoning, and correcting their mistakes as more computation or interaction is available. Even the…

Verification-guided self-improvement has recently emerged as a promising approach to improving the accuracy of large language model (LLM) outputs. However, existing approaches face a trade-off between inference efficiency and accuracy:…

Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability to follow natural-language instructions, while powerful, also makes them vulnerable to a new…

Accurate mathematical reasoning with Large Language Models (LLMs) is crucial in revolutionizing domains that heavily rely on such reasoning. However, LLMs often encounter difficulties in certain aspects of mathematical reasoning, leading to…

Aligning Large Language Models (LLMs) with human intentions and values is crucial yet challenging. Current methods primarily rely on human preferences, which are costly and insufficient in capturing nuanced feedback expressed in natural…

Self-training approach for large language models (LLMs) improves reasoning abilities by training the models on their self-generated rationales. Previous approaches have labeled rationales that produce correct answers for a given question as…

The reflection capacity of Large Language Model (LLM) has garnered extensive attention. A post-hoc prompting strategy, e.g., reflexion and self-refine, refines LLM's response based on self-evaluated or external feedback. However, recent…

Self-correction is essential for solving complex reasoning problems in vision-language models (VLMs). However, existing reinforcement learning (RL) methods struggle to learn it, as effective self-correction behaviors emerge only rarely,…

We consider learning in an adversarial Markov Decision Process (MDP) where the loss functions can change arbitrarily over $K$ episodes and the state space can be arbitrarily large. We assume that the Q-function of any policy is linear in…

As large language models (LLMs) often generate plausible but incorrect content, error detection has become increasingly critical to ensure truthfulness. However, existing detection methods often overlook a critical problem we term as…

Reward modeling is crucial for aligning large language models (LLMs) with human preferences, especially in reinforcement learning from human feedback (RLHF). However, current reward models mainly produce scalar scores and struggle to…

Maintaining reliable UI test suites in large-scale enterprise applications is a persistent and costly challenge. We present an industrial case study of a multi-agent autonomous testing system evaluated using anonymized execution data from a…

LLM-generated drafts often contain subtle factual or logical errors, yet prior work shows that models struggle to reliably integrate multi-turn feedback aimed at fixing them. We propose in-place feedback, an interaction paradigm in which…

Proactive interventions by LLM critic models are often assumed to improve reliability, yet their effects at deployment time are poorly understood. We show that a binary LLM critic with strong offline accuracy (AUROC 0.94) can nevertheless…

Large language models can answer causal questions correctly for the wrong reasons. Current RL methods reward \emph{what} a model concludes but ignore \emph{why}, reinforcing correlational shortcuts -- a failure we call \emph{Reward…

End-to-end engineering design pipelines, in which designs are evaluated using concurrently defined optimal controllers, are becoming increasingly common in practice. To discover designs that perform well even under the misspecification of…

Code repair is a fundamental task in software development, facilitating efficient bug resolution and software maintenance. Although large language models (LLMs) have demonstrated considerable potential in automated code repair, their…

We introduce GIER (Gap-driven Iterative Enhancement of Responses), a general framework for improving large language model (LLM) outputs through self-reflection and revision based on conceptual quality criteria. Unlike prompting strategies…

We consider the problem of online control of systems with time-varying linear dynamics. This is a general formulation that is motivated by the use of local linearization in control of nonlinear dynamical systems. To state meaningful…