Related papers: History-Aware Reasoning for GUI Agents

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. With the paradigm shift toward self-evolving agentic learning, models are increasingly expected…

Despite the promise of Retrieval-Augmented Generation in grounding Multimodal Large Language Models with external knowledge, the transition to extensive contexts often leads to significant attention dilution and reasoning hallucinations.…

Retrieval-augmented generation with tool-calling agents (agentic RAG) has become increasingly powerful in understanding, processing, and responding to user queries. However, the scope of the grounding knowledge is limited and asking…

Long-form video understanding remains fundamentally challenged by pervasive spatiotemporal redundancy and intricate narrative dependencies that span extended temporal horizons. While recent structured representations compress visual…

Advancements in the capabilities of Large Language Models (LLMs) have created a promising foundation for developing autonomous agents. With the right tools, these agents could learn to solve tasks in new environments by accumulating and…

With the rapid development of Large Vision Language Models, the focus of Graphical User Interface (GUI) agent tasks shifts from single-screen tasks to complex screen navigation challenges. However, real-world GUI environments, such as PC…

In order for large language models to achieve true conversational continuity and benefit from experiential learning, they need memory. While research has focused on the development of complex memory systems, it remains unclear which types…

Large language models show promise for embodying historical characters in dialogue systems, but existing approaches face a critical trade-off: simple retrieval-augmented generation produces shallow responses, while multi-stage reflection…

Deep Reinforcement Learning (RL) involves the use of Deep Neural Networks (DNNs) to make sequential decisions in order to maximize reward. For many tasks the resulting sequence of actions produced by a Deep RL policy can be long and…

Long-term memory is one of the key factors influencing the reasoning capabilities of Large Language Model Agents (LLM Agents). Incorporating a memory mechanism that effectively integrates past interactions can significantly enhance…

Multi-modal multi-agent systems (MM-MAS) have gained increasing attention for their capacity to enable complex reasoning and coordination across diverse modalities. As these systems continue to expand in scale and functionality,…

We propose GAM-Agent, a game-theoretic multi-agent framework for enhancing vision-language reasoning. Unlike prior single-agent or monolithic models, GAM-Agent formulates the reasoning process as a non-zero-sum game between base…

Schemas -- abstract relational structures that capture the commonalities across experiences -- are thought to underlie humans' and animals' ability to rapidly generalize knowledge, rebind new experiences to existing structures, and flexibly…

Incident response (IR) requires fast, coordinated, and well-informed decision-making to contain and mitigate cyber threats. While large language models (LLMs) have shown promise as autonomous agents in simulated IR settings, their reasoning…

Reinforcement learning agents deployed in the real world often have to cope with partially observable environments. Therefore, most agents employ memory mechanisms to approximate the state of the environment. Recently, there have been…

Despite rapid progress, embodied agents still struggle with long-horizon manipulation that requires maintaining spatial consistency, causal dependencies, and goal constraints. A key limitation of existing approaches is that task reasoning…

Autonomous Graphical User Interface (GUI) agents often struggle with multi-step tasks due to constrained context windows and static policies that fail to adapt to dynamic environments. To address these limitations, this work proposes the…

Automating operations research (OR) with large language models (LLMs) remains limited by hand-crafted reasoning--execution workflows. Complex OR tasks require adaptive coordination among problem interpretation, mathematical formulation,…

Long-horizon interactive agents often accumulate large trajectory histories yet still fail to answer questions about earlier events reliably. We argue that the main bottleneck is not context length alone, but the trajectory-to-answer…

The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requires maintaining rigorous logical integrity over extended horizons. However, prevalent memory…