Related papers: Scaling Long-Horizon LLM Agent via Context-Folding

The rapid evolution of Multi-modal Large Language Models (MLLMs) has advanced workflow automation; however, existing research mainly targets performance upper bounds in static environments, overlooking robustness for stochastic real-world…

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies,…

Scaling laws have transformed our understanding of large language models by linking upstream metrics like cross-entropy loss to design factors such as model size, training data, and compute. However, these conventional laws fail to capture…

Spreadsheets are ubiquitous across the World Wide Web, playing a critical role in enhancing work efficiency across various domains. Large language model (LLM) has been recently attempted for automatic spreadsheet manipulation but has not…

Large language model (LLM) agents often struggle in long-context interactions. As the agent accumulates more interaction history, context management approaches such as sliding window and prompt compression may omit earlier structured…

The emergence of Large Language Models (LLMs) like ChatGPT has inspired the development of LLM-based agents capable of addressing complex, real-world tasks. However, these agents often struggle during task execution due to methodological…

LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promising solution is to encode context as continuous embeddings rather than discrete tokens,…

Researchers and practitioners have recently reframed powerful Large Language Models (LLMs) as agents, enabling them to automate complex tasks largely via the use of specialized functions. To facilitate the development of LLM agents, we…

Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limited toolsets,…

Modern information systems require autonomous agents capable of navigating complex workflows, yet current methodologies often struggle with the transition from structured metadata parsing to general environmental perception. While the…

Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks. However, in real-world scenarios, cooperation among individuals is often…

We study the in-context learning dynamics of large language models (LLMs) using three instrumental learning tasks adapted from cognitive psychology. We find that LLMs update their beliefs in an asymmetric manner and learn more from…

Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we propose Extensible…

Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks. However, the robustness of these…

Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering. As these systems become more autonomous and are deployed at scale, understanding why an…

Large Language Model (LLM) agents show great promise for complex, multi-turn tool-use tasks, but their development is often hampered by the extreme scarcity of high-quality training data. Supervised fine-tuning (SFT) on synthetic data leads…

Large language model (LLM) agents have recently demonstrated strong capabilities in interactive decision-making, yet they remain fundamentally limited in long-horizon tasks that require structured planning and reliable execution. Existing…

Decision making demands intricate interplay between perception, memory, and reasoning to discern optimal policies. Conventional approaches to decision making face challenges related to low sample efficiency and poor generalization. In…

Embodied agents operating in household environments must interpret ambiguous and under-specified human instructions. A capable household robot should recognize ambiguity and ask relevant clarification questions to infer the user intent…

Recent months have seen the emergence of a powerful new trend in which large language models (LLMs) are augmented to become autonomous language agents capable of performing objective oriented multi-step tasks on their own, rather than…