相关论文: Probabilistic Active Goal Recognition

Conventional Reinforcement Learning (RL) algorithms, typically focused on estimating or maximizing expected returns, face challenges when refining offline pretrained models with online experiences. This paper introduces Generative Actor…

Modern large-scale ranking systems operate within a sophisticated landscape of competing objectives, operational constraints, and evolving product requirements. Progress in this domain is increasingly bottlenecked by the engineering context…

Symbolic regression aims to discover concise, interpretable mathematical expressions that satisfy desired objectives, such as fitting data, posing a highly combinatorial optimization problem. While genetic programming has been the dominant…

Reciprocating interactions represent a central feature of all human exchanges. They have been the target of various recent experiments, with healthy participants and psychiatric populations engaging as dyads in multi-round exchanges such as…

Among the research topics in multi-agent learning, mixed-motive cooperation is one of the most prominent challenges, primarily due to the mismatch between individual and collective goals. The cutting-edge research is focused on…

The problem of anticipating human actions is an inherently uncertain one. However, we can reduce this uncertainty if we have a sense of the goal that the actor is trying to achieve. Here, we present an action anticipation model that…

While Retrieval-Augmented Generation (RAG) plays a crucial role in the application of Large Language Models (LLMs), existing retrieval methods in knowledge-dense domains like law and medicine still suffer from a lack of multi-perspective…

We propose a new framework for multi-agent reinforcement learning (MARL), where the agents cooperate in a time-evolving network with latent community structures and mixed memberships. Unlike traditional neighbor-based or fixed interaction…

Reliable retrieval-augmented generation (RAG) systems depend fundamentally on the retriever's ability to find relevant information. We show that neural retrievers used in RAG systems have blind spots, which we define as the failure to…

Monte Carlo Tree Search (MCTS) has emerged as a powerful tool for decision-making in robotics, enabling efficient exploration of large search spaces. However, traditional MCTS methods struggle in environments characterized by high…

Goal-conditioned reinforcement learning (GCRL) allows agents to learn diverse objectives using a unified policy. The success of GCRL, however, is contingent on the choice of goal representation. In this work, we propose a mask-based goal…

We present a method for active inference with partial observations in stochastic systems through incentive design, also known as the leader-follower game. Consider a leader agent who aims to infer a follower agent's type given a finite set…

Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a difficult challenge.…

Existing multi-agent perception systems assume that every agent utilizes the same model with identical parameters and architecture. The performance can be degraded with different perception models due to the mismatch in their confidence…

The central tenet of reinforcement learning (RL) is that agents seek to maximize the sum of cumulative rewards. In contrast, active inference, an emerging framework within cognitive and computational neuroscience, proposes that agents act…

Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access external knowledge sources, but the effectiveness of RAG relies on the coordination between the retriever and the generator. Since these components are…

Agentic Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by enabling dynamic, multi-step reasoning and information retrieval. However, these systems often exhibit sub-optimal search behaviors like…

Recent approaches to goal recognition have leveraged planning landmarks to achieve high-accuracy with low runtime cost. These approaches, however, lack a probabilistic interpretation. Furthermore, while most probabilistic models to goal…

Recent advancements in large language models (LLMs) have shown remarkable potential in automating machine learning tasks. However, existing LLM-based agents often struggle with low-diversity and suboptimal code generation. While recent work…

Generalized Rapid Action Value Estimation (GRAVE) has been shown to be a strong variant within the Monte-Carlo Tree Search (MCTS) family of algorithms for General Game Playing (GGP). However, its reliance on storing additional win/visit…