Related papers: Latent State Estimation Helps UI Agents to Reason

Can emergent language models faithfully model the intelligence of decision-making agents? Though modern language models exhibit already some reasoning ability, and theoretically can potentially express any probable distribution over tokens,…

Recently, Large Language Models (LLMs) have emerged as an alternative to training task-specific dialog agents, due to their broad reasoning capabilities and performance in zero-shot learning scenarios. However, many LLM-based dialog systems…

As general-purpose tools, Large Language Models (LLMs) must often reason about everyday physical environments. In a question-and-answer capacity, understanding the interactions of physical objects may be necessary to give appropriate…

We introduce AgenticSimLaw, a role-structured, multi-agent debate framework that provides transparent and controllable test-time reasoning for high-stakes tabular decision-making tasks. Unlike black-box approaches, our courtroom-style…

Recent advances in large language models (LLMs) have facilitated the widespread deployment of LLMs as interactive agents capable of reasoning, planning, and tool use. Despite strong performance on existing benchmarks, such agents often…

Test-time scaling (TTS) has become an effective approach for improving large language model performance by allocating additional computation during inference. However, existing TTS strategies are largely hand-crafted: researchers manually…

Owing to the capability of in-context learning, large language models (LLMs) have shown impressive performance across diverse mathematical reasoning benchmarks. However, we find that few-shot demonstrations can sometimes bring negative…

Predicting group behavior, how individuals coordinate, communicate, and interact during collaborative tasks, is essential for designing systems that can support team performance through real-time prediction and realistic simulation of…

Recent advancements in Large Language Models (LLMs) have spurred interest in deploying LLM agents to undertake tasks in the world. LLMs are often deployed in agent systems: code that orchestrates LLM calls and provides them with tools. We…

Large language models (LLMs) have been increasingly employed for (interactive) decision-making, via the development of LLM-based autonomous agents. Despite their emerging successes, the performance of LLM agents in decision-making has not…

Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit…

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…

Answering complex natural language questions often necessitates multi-step reasoning and integrating external information. Several systems have combined knowledge retrieval with a large language model (LLM) to answer such questions. These…

Autonomous agent systems powered by Large Language Models (LLMs) have demonstrated promising capabilities in automating complex tasks. However, current evaluations largely rely on success rates without systematically analyzing the…

Multi-agent LLM systems improve reasoning by combining outputs from multiple agents, but interaction-heavy methods can introduce error propagation and high communication overhead. When agents exchange raw responses or reasoning traces,…

As large language model (LLM)-based agents become increasingly integrated into daily digital interactions, their ability to reason across long interaction histories becomes crucial for providing personalized and contextually aware…

Continuous latent-space reasoning offers a compact alternative to textual chain-of-thought for multimodal models, enabling high-dimensional visual evidence to be integrated without explicit reasoning tokens. However, we identify a…

Historically, scientific discovery has been a lengthy and costly process, demanding substantial time and resources from initial conception to final results. To accelerate scientific discovery, reduce research costs, and improve research…

Large language models (LLMs) have brought autonomous agents closer to artificial general intelligence (AGI) due to their promising generalization and emergent capabilities. There is, however, a lack of studies on how LLM-based agents…

LLMs-based agents increasingly operate in multi-agent environments where strategic interaction and coordination are required. While existing work has largely focused on individual agents or on interacting agents sharing explicit…