Related papers: IMPACT-CYCLE: A Contract-Based Multi-Agent System …

We study offline imitation learning (IL) in cooperative multi-agent settings, where demonstrations have unlabeled mixed quality - containing both expert and suboptimal trajectories. Our proposed solution is structured in two stages:…

Relevance is a foundation of user experience in e-commerce search. We view relevance optimization as a closed-loop ecosystem involving multiple human roles: users who provide feedback, product managers who define standards, annotators who…

The advancement of Large Language Models (LLMs) enables flexible and interpretable automatic evaluations. In the field of machine translation evaluation, utilizing LLMs with translation error annotations based on Multidimensional Quality…

Understanding long-form egocentric videos remains challenging for multimodal large language models (MLLMs) due to limited context length and insufficient grounding of fine-grained visual details. The recently proposed HD-EPIC benchmark…

Long-term Action Quality Assessment (AQA) evaluates the execution of activities in videos. However, the length presents challenges in fine-grained interpretability, with current AQA methods typically producing a single score by averaging…

The rapid development of diffusion models has greatly advanced AI-generated videos in terms of length and consistency recently, yet assessing AI-generated videos still remains challenging. Previous approaches have often focused on…

While text-to-video diffusion models have advanced significantly, creating coherent long-form content remains unreliable due to stochastic sampling artifacts. This necessitates generating multiple candidates, yet verifying them creates a…

Existing Large Language Model (LLM) agents struggle in interactive environments requiring long-horizon planning, primarily due to compounding errors when simulating future states. To address this, we propose ProAct, a framework that enables…

AI applications increasingly depend on long-context inference, where LLMs consume substantial context to support stronger reasoning. Common examples include retrieval-augmented generation, agent memory layers, and multi-agent orchestration.…

Current LLM agents operate under an implicit but universal assumption: execution is a transaction -- the user submits a request, the agent works in isolation, and only upon completion does the dialogue resume. This forces users into a…

This study addresses the challenges of dynamics and complexity in intelligent human-computer interaction and proposes a reinforcement learning-based optimization framework to improve long-term returns and overall experience. Human-computer…

Computer-use agents can operate computers and automate laborious tasks, but despite recent rapid progress, they still lag behind human users, especially when tasks require domain-specific procedural knowledge about particular applications,…

Amodal completion, the task of inferring invisible object parts, faces significant challenges in maintaining semantic consistency and structural integrity. Prior progressive approaches are inherently limited by inference instability and…

Poor interpretability hinders the practical applicability of multi-agent reinforcement learning (MARL) policies. Deploying interpretable surrogates of uninterpretable policies enhances the safety and verifiability of MARL for real-world…

Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free methods face a trade-off between capacity and precision: end-to-end models…

Accurate driving behavior recognition and reasoning are critical for autonomous driving video understanding. However, existing methods often tend to dig out the shallow causal, fail to address spurious correlations across modalities, and…

Video enhancement is a challenging problem, more than that of stills, mainly due to high computational cost, larger data volumes and the difficulty of achieving consistency in the spatio-temporal domain. In practice, these challenges are…

Video question answering (VideoQA) is a challenging task that requires integrating spatial, temporal, and semantic information to capture the complex dynamics of video sequences. Although recent advances have introduced various approaches…

Autonomous coding agents, powered by large language models (LLMs), are increasingly being adopted in the software industry to automate complex engineering tasks. However, these agents are prone to a wide range of misbehaviors, such as…

Large Language Models (LLMs) with extended context windows promise direct reasoning over long documents, reducing the need for chunking or retrieval. Constructing annotated resources for training and evaluation, however, remains costly.…