Related papers: STAR : Bridging Statistical and Agentic Reasoning …

Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL) that reason and act in interactive environments. However, sparse and sometimes unverifiable rewards make it extremely…

Large Language Models (LLMs) tend to generate a long reasoning chain when solving complex tasks. However, as the reasoning chain extends, critical intermediate steps and the original prompt will be buried in the context, receiving…

Looped Language Models (LoopLMs) enable efficient latent reasoning through depth recurrence, yet exhibit unreliable test-time scaling behavior: performance often peaks at a certain iteration depth and then collapses with further recurrence.…

Aligning large language models (LLMs) with human values is crucial for safe deployment. Inference-time techniques offer granular control over generation; however, they rely on model uncertainty, meaning an internal estimate of how likely…

Large Language Model (LLM) inference systems present significant challenges in statistical performance characterization due to dynamic workload variations, diverse hardware architectures, and complex interactions between model size, batch…

Multimodal large language models excel across diverse domains but struggle with complex visual reasoning tasks. To enhance their reasoning capabilities, current approaches typically rely on explicit search or post-training techniques.…

This paper introduces STAR-1, a high-quality, just-1k-scale safety dataset specifically designed for large reasoning models (LRMs) like DeepSeek-R1. Built on three core principles -- diversity, deliberative reasoning, and rigorous filtering…

The evaluation of large language models (LLMs) has predominantly relied on static datasets, which offer limited scalability and fail to capture the evolving reasoning capabilities of recent models. To overcome these limitations, we propose…

Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…

Language Models (LMs) are widely used in software engineering for code generation, but they may produce erroneous code. Rather than repairing outputs, a more thorough remedy is to address underlying model failures. LM repair offers a…

Although Large Language Models (LLMs) achieve remarkable performance across various tasks, they often struggle with complex reasoning tasks, such as answering mathematical questions. Recent efforts to address this issue have primarily…

As machine learning models are increasingly deployed in high-stakes domains, the need for interpretability has grown to meet strict regulatory and accountability constraints. Despite this interest, systematic evaluations of inherently…

Generating step-by-step "chain-of-thought" rationales improves language model performance on complex reasoning tasks like mathematics or commonsense question-answering. However, inducing language model rationale generation currently…

Context-dependent semantic parsing has proven to be an important yet challenging task. To leverage the advances in context-independent semantic parsing, we propose to perform follow-up query analysis, aiming to restate context-dependent…

Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS). Yet, they face significant challenges in complex domains. Error propagation from incorrect intermediate reasoning can lead to false positives for…

Recent advances in Large Language Models (LLMs) and Large Reasoning Models (LRMs) have enabled agentic search systems that interleave multi-step reasoning with external tool use. However, existing frameworks largely rely on unstructured…

The creation of high-quality datasets to improve Large Language Model (LLM) reasoning remains a significant challenge, as current methods often suffer from generating low-quality/incorrect answers and limited information richness from…

Real-world ecommerce recommender systems must deliver relevant items under strict tens-of-milliseconds latency constraints despite challenges such as cold-start products, rapidly shifting user intent, and dynamic context including…

Large language models (LLMs) exhibit strong capabilities as decision-making agents by interleaving reasoning and actions, as seen in ReAct-style frameworks. Yet, their practical deployment is constrained by high inference costs and large…

Entity Linking (EL) has traditionally relied on large annotated datasets and extensive model fine-tuning. While recent few-shot methods leverage large language models (LLMs) through prompting to reduce training requirements, they often…