Related papers: Decocted Experience Improves Test-Time Inference i…

As Large Language Models (LLMs) gain agentic abilities, they will have to navigate complex multi-agent scenarios, interacting with human users and other agents in cooperative and competitive settings. This will require new reasoning skills,…

Due to their ability to process long and complex contexts, LLMs can offer key benefits to the Legal domain, but their adoption has been hindered by their tendency to generate unfaithful, ungrounded, or hallucinatory outputs. While…

Long-context modeling capabilities are important for large language models (LLMs) in various applications. However, directly training LLMs with long context windows is insufficient to enhance this capability since some training samples do…

Designing effective collaboration structure for multi-agent LLM systems to enhance collective reasoning is crucial yet remains under-explored. In this paper, we systematically investigate how collaborative reasoning performance is affected…

Research on large language models (LLMs) has shown remarkable performance in domains such as mathematics, programming, and literary creation. However, most studies have focused on semantic memory-based question answering, neglecting LLMs'…

Performance metrics-driven context caching has a profound impact on throughput and response time in distributed context management systems for real-time context queries. This paper proposes a reinforcement learning based approach to…

While most existing works on LLM prompting techniques focus only on how to select a better set of data samples inside one single prompt input (In-Context Learning or ICL), why can not we design and leverage multiple prompts together to…

With this paper, we survey techniques for improving the predictive accuracy of pretrained large language models by allocating additional compute at inference time. In categorizing test-time scaling methods, we place special emphasis on how…

Recent advances in speech large language models (speech LLMs) have enabled seamless spoken interactions, but these systems still struggle with complex reasoning tasks. Previously, chain-of-thought (CoT) prompting or fine-tuning has been to…

Optimizing software performance through automated code refinement offers a promising avenue for enhancing execution speed and efficiency. Despite recent advancements in LLMs, a significant gap remains in their ability to perform in-depth…

When are multi-agent LLM systems merely a collection of individual agents versus an integrated collective with higher-order structure? We introduce an information-theoretic framework to test -- in a purely data-driven way -- whether…

Large language models (LLMs) have demonstrated strong potential and impressive performance in automating the generation and optimization of workflows. However, existing approaches are marked by limited reasoning capabilities, high…

Large language model agents are becoming increasingly capable at web-centric tasks such as information retrieval, complex reasoning. These emerging capabilities have given rise to surge research interests in developing LLM agent for…

Detecting evidence within the context is a key step in the process of reasoning task. Evaluating and enhancing the capabilities of LLMs in evidence detection will strengthen context-based reasoning performance. This paper proposes a…

Human reasoning is shaped by resource rationality -- optimizing performance under constraints. Recently, inference-time scaling has emerged as a powerful paradigm to improve the reasoning performance of Large Language Models by expanding…

Sparsity has long been a central theme in LLM efficiency, but its role in context processing remains unresolved. As LLM workloads shift toward longer contexts and agentic interactions, the compute and memory bottlenecks of attention become…

In recent years, the input context sizes of large language models (LLMs) have increased dramatically. However, existing evaluation methods have not kept pace, failing to comprehensively assess the efficiency of models in handling long…

Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training…

Large language models (LLMs) are increasingly deployed as agents in dynamic, real-world environments, where success requires both reasoning and effective tool use. A central challenge for agentic tasks is the growing context length, as…

While agent evaluation has shifted toward long-horizon tasks, most benchmarks still emphasize local, step-level reasoning rather than the global constrained optimization (e.g., time and financial budgets) that demands genuine planning…