Related papers: When Missing Becomes Structure: Intent-Preserving …

To accurately understand the intention of an utterance is crucial in conversational communication. As conversational artificial intelligence models are rapidly being developed and applied in various fields, it is important to evaluate the…

Intention sharing is crucial for efficient cooperation under partially observable environments in multi-agent reinforcement learning (MARL). However, message deceiving, i.e., a mismatch between the propagated intentions and the final…

Deep Research (DR) agents extend Large Language Models (LLMs) beyond parametric knowledge by autonomously retrieving and synthesizing evidence from large web corpora into long-form reports, enabling a long-horizon agentic paradigm. However,…

Policy learning (PL) is a module of a task-oriented dialogue system that trains an agent to make actions in each dialogue turn. Imitating human action is a fundamental problem of PL. However, both supervised learning (SL) and reinforcement…

Goal-conditioned reinforcement learning endows an agent with a large variety of skills, but it often struggles to solve tasks that require more temporally extended reasoning. In this work, we propose to incorporate imagined subgoals into…

Effectively leveraging large, previously collected datasets in reinforcement learning (RL) is a key challenge for large-scale real-world applications. Offline RL algorithms promise to learn effective policies from previously-collected,…

Large language models (LLMs) exhibit persistent miscalibration, especially after instruction tuning and preference alignment. Modified training objectives can improve calibration, but retraining is expensive. Inference-time steering offers…

New intent discovery (NID) seeks to recognize both new and known intents from unlabeled user utterances, which finds prevalent use in practical dialogue systems. Existing works towards NID mainly adopt a cascaded architecture, wherein the…

Offline inverse reinforcement learning (IRL) aims to recover a reward function that explains expert behavior using only fixed demonstration data, without any additional online interaction. We propose BiCQL-ML, a policy-free offline IRL…

Event-driven scheduling policies are increasingly deployed in industrial environments, where decisions are made under asynchronous and partially observed system states. As a result, decision states are not temporally consistent, action…

Social learning is a fundamental mechanism shaping decision-making across numerous social networks, including social trading platforms. In those platforms, investors combine traditional investing with copying the behavior of others.…

Chain-of-Thought (CoT) reasoning enhances large language models (LLMs) by decomposing complex problems into step-by-step solutions, improving performance on reasoning tasks. However, current CoT disclosure policies vary widely across…

Semantic communications will play a critical role in enabling goal-oriented services over next-generation wireless systems. However, most prior art in this domain is restricted to specific applications (e.g., text or image), and it does not…

Chain-of-thought (CoT) traces are increasingly used both to improve language model capability and to audit model behavior, implicitly assuming that the visible trace remains synchronized with the computation that determines the answer. We…

Multi-modal class-incremental learning (MMCIL) seeks to leverage multi-modal data, such as audio-visual and image-text pairs, thereby enabling models to learn continuously across a sequence of tasks while mitigating forgetting. While…

We present Future-KL Influenced Policy Optimization (FIPO), a reinforcement learning algorithm designed to overcome reasoning bottlenecks in large language models. While GRPO style training scales effectively, it typically relies on…

Dialogue state trackers have made significant progress on benchmark datasets, but their generalization capability to novel and realistic scenarios beyond the held-out conversations is less understood. We propose controllable counterfactuals…

We present a probabilistic intent modeling framework for large language model (LLM) agents in multi-turn social dialogue. The framework maintains a belief distribution over a partner's latent intentions, initialized from contextual priors…

Continuous-action policies trained on a single demonstrated trajectory per scene suffer from mode collapse: samples cluster around the demonstrated maneuver and the policy cannot represent semantically distinct alternatives. Under…

Large language models (LLMs) often solve challenging math exercises yet fail to apply the concept right when the problem requires genuine understanding. Popular Reinforcement Learning with Verifiable Rewards (RLVR) pipelines reinforce final…