相关论文: Detecting and Mitigating the Correct-Answer Extinc…

Large Language Models (LLMs) are increasingly relied upon for solving complex reasoning tasks in domains such as mathematics, logic, and multi-step question answering. A growing line of work seeks to improve reasoning quality by scaling…

Reinforcement learning post-training has substantially improved the reasoning accuracy of vision-language models, yet the resulting policies remain poorly calibrated. Terminal correctness rewards provide no gradient that penalizes confident…

Under voltage load shedding has been considered as a standard approach to recover the voltage stability of the electric power grid under emergency conditions, yet this scheme usually trips a massive amount of load inefficiently.…

Recent advancements in large language models (LLMs) integrated with external tools and APIs have successfully addressed complex tasks by using in-context learning or fine-tuning. Despite this progress, the vast scale of tool retrieval…

Large language models excel at complex tasks by breaking down problems into structured reasoning steps. However, reasoning traces often extend beyond reaching a correct answer, causing wasted computation, reduced readability, and…

Reinforcement learning (RL) has become a central paradigm for post-training large language models (LLMs), particularly for complex reasoning tasks, yet it often suffers from exploration collapse: policies prematurely concentrate on a small…

Building deep reinforcement learning (RL) agents that find a good policy with few samples has proven notoriously challenging. To achieve sample efficiency, recent work has explored updating neural networks with large numbers of gradient…

Group Relative Policy Optimization (GRPO) has become the dominant method for reinforcement learning with verifiable rewards in large language models, but it suffers from two critical limitations: gradient vanishing and diversity collapse.…

Reinforcement learning with verifiable rewards has significantly advanced the reasoning capabilities of large language models, yet how to explicitly steer training toward exploration or exploitation remains an open problem. We introduce…

We introduce a control-tutored reinforcement learning (CTRL) algorithm. The idea is to enhance tabular learning algorithms so as to improve the exploration of the state-space, and substantially reduce learning times by leveraging some…

Autonomous systems increasingly rely on human feedback to align their behavior, expressed as pairwise comparisons, rankings, or demonstrations. While existing methods can adapt behaviors, they often fail to guarantee safety in…

Large Language Models (LLMs) often produce inconsistent answers when faced with different phrasings of the same prompt. In this paper, we propose Flip-Flop Consistency ($F^2C$), an unsupervised training method that improves robustness to…

Model-based reinforcement learning (MBRL) improves sample efficiency by optimizing policies inside imagined rollouts, but long-horizon planning degrades when model errors compound and imagined trajectories drift off the training manifold.…

Motivated by the episodic version of the classical inventory control problem, we propose a new Q-learning-based algorithm, Elimination-Based Half-Q-Learning (HQL), that enjoys improved efficiency over existing algorithms for a wide variety…

Vision-Language Models (VLMs) frequently suffer from visual perception errors and hallucinations that compromise answer accuracy in complex reasoning tasks. Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising solution…

Large Language Models (LLMs) are emerging as versatile foundation models for computational chemistry, handling bidirectional tasks like reaction prediction and retrosynthesis. However, these models often lack round-trip consistency. For…

Reasoning models improve their problem-solving ability through inference-time scaling, allocating more compute via longer token budgets. Identifying which reasoning traces are likely to succeed remains a key opportunity: reliably predicting…

Reinforcement learning with verifiable rewards (RLVR) has shown great promise in enhancing the reasoning abilities of large reasoning models (LRMs). However, it suffers from a critical issue: entropy collapse and premature convergence.…

Deep Reinforcement Learning (DRL) has become a popular method for solving control problems in power systems. Conventional DRL encourages the agent to explore various policies encoded in a neural network (NN) with the goal of maximizing the…

Test-time scaling methods have seen a rapid increase in popularity for its computational efficiency and parameter-independent training to improve reasoning performance on Large Language Models. One such method is called budget forcing, a…