Related papers: EAGer: Entropy-Aware GEneRation for Adaptive Infer…

Test-time scaling has significantly improved large language model performance, enabling deeper reasoning to solve complex problems. However, this increased reasoning capability also leads to excessive token generation and unnecessary…

Reinforcement learning has become the standard for improving reasoning in large language models, yet evidence increasingly suggests that RL does not teach new strategies; it redistributes probability mass over solutions the base model…

Large Language Models have seen increasing use in various software development tasks, especially in code generation. The most advanced recent methods attempt to incorporate feedback from code execution into prompts to help guide LLMs in…

Test time adaptation (TTA) equips deep learning models to handle unseen test data that deviates from the training distribution, even when source data is inaccessible. While traditional TTA methods often rely on entropy as a confidence…

Unified Multimodal Models (UMMs) exhibit strong understanding, yet this capability often fails to effectively guide generation. We identify this as a Cognitive Gap: the model lacks the understanding of how to enhance its own generation…

Recent advancements in Large Language Models (LLMs) have leveraged increased test-time computation to enhance reasoning capabilities, a strategy that, while effective, incurs significant latency and resource costs, limiting their…

Large language models (LLMs) excel at many language understanding tasks but struggle to reason over knowledge that evolves. To address this, recent work has explored augmenting LLMs with knowledge graphs (KGs) to provide structured,…

Test-time scaling improves the inference performance of Large Language Models (LLMs) but also incurs substantial computational costs. Although recent studies have reduced token consumption through dynamic self-consistency, they remain…

Large language model (LLM) agents often suffer from high reasoning overhead, excessive token consumption, unstable execution, and inability to reuse past experiences in complex tasks like business queries, tool use, and workflow…

Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertainty, is highly correlated with VLM reliability. While prior entropy-based attacks maximize…

Retrieval-Augmented Generation (RAG) systems for Large Language Models (LLMs) hold promise in knowledge-intensive tasks but face limitations in complex multi-step reasoning. While recent methods have integrated RAG with chain-of-thought…

Recent advancements in large language models (LLMs) often rely on generating intermediate reasoning steps to enhance accuracy. However, little work has examined how reasoning utility contributes to the final answer's correctness. Due to the…

Reinforcement Learning with Verifiable Rewards (RLVR) has become a central approach for improving the reasoning ability of large language models. Recent work studies RLVR through token entropy, arguing that high-entropy tokens drive…

Large language models (LLMs) have recently shown strong progress on scientific reasoning, yet two major bottlenecks remain. First, explicit retrieval fragments reasoning, imposing a hidden "tool tax" of extra tokens and steps. Second,…

While large language models (LLMs) show great potential in temporal reasoning, most existing work focuses heavily on enhancing performance, often neglecting the explainable reasoning processes underlying the results. To address this gap, we…

Text embedding and generative tasks are usually trained separately based on large language models (LLMs) nowadays. This causes a large amount of training cost and deployment effort. Context compression is also a challenging and pressing…

This paper addresses the challenge of comprehending very long contexts in Large Language Models (LLMs) by proposing a method that emulates Retrieval Augmented Generation (RAG) through specialized prompt engineering and chain-of-thought…

Automated patent claim validation demands low error tolerance. However, existing approaches face a rigidity-resource dilemma: lightweight encoders cannot track long-range legal dependencies, while exhaustive LLM verification incurs 4-5X…

Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency. We introduce Efficient Selective Language Modeling (ESLM), a risk-aware algorithm that improves training…

Agentic Test-Time Scaling (TTS) has delivered state-of-the-art (SOTA) performance on complex software engineering tasks such as code generation and bug fixing. However, its practical adoption remains limited due to significant computational…