Related papers: Beyond the Attention Stability Boundary: Agentic S…

Longitudinal health agents must reason across multi-source trajectories that combine continuous device streams, sparse clinical exams, and episodic life events - yet evaluating them is hard: real-world data cannot be released at scale, and…

Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks. However, their performance…

Training large language models as retrieval-augmented reasoning agents typically combines reinforcement learning with an SFT cold start distilled from a stronger model. However, this paradigm overlooks two fundamental factors: the…

Large reasoning models (LRMs) achieve strong performance through extended reasoning traces, but they often exhibit overthinking behavior for low-complexity queries. Existing efforts to mitigate this issue are fundamentally limited by…

As autonomous and agentic AI systems scale in robotic and human-machine environments, managing hallucination and persistent but unjustified action remains an open challenge. Rather than attributing these failures solely to model or…

We present a controlled study of multi-hop contextual reasoning in large language models, providing a clean demonstration of the task-method dissociation: rule-based pattern matching achieves 100% success on structured information retrieval…

Large language models perform well on many reasoning tasks, yet they often lack awareness of whether their current knowledge or reasoning state is complete. In non-interactive puzzle settings, the narrative is fixed and the underlying…

Transformer-based architectures achieve state-of-the-art performance across a wide range of tasks in natural language processing, computer vision, and speech processing. However, their immense capacity often leads to overfitting, especially…

Recent advances in agentic Large Language Models (LLMs) have positioned them as generalist planners capable of reasoning and acting across diverse tasks. However, existing agent benchmarks largely focus on symbolic or weakly grounded…

As large language models (LLMs) evolve into autonomous agents, evaluating repository-level reasoning, the ability to maintain logical consistency across massive, real-world, interdependent file systems, has become critical. Current…

Data preparation, which aims to transform heterogeneous and noisy raw tables into analysis-ready data, remains a major bottleneck in data science. Recent approaches leverage large language models (LLMs) to automate data preparation from…

Retrieval-Augmented Generation (RAG) extends large language models (LLMs) beyond parametric knowledge, yet it is unclear when iterative retrieval-reasoning loops meaningfully outperform static RAG, particularly in scientific domains with…

Test-Time Scaling (TTS) has significantly enhanced the capabilities of Large Reasoning Models (LRMs) but introduces a critical side-effect known as Overthinking. We conduct a preliminary study to rethink this phenomenon from a fine-grained…

Answer set programming (ASP) aims to realize the AI vision: The user specifies the problem, and the computer solves it. Indeed, ASP has made this vision true in many application domains. However, will current ASP solving techniques scale up…

LLM agents are rapidly evolving from coding assistants into autonomous software engineering systems. However, existing evaluation methodologies remain largely centered on static, isolated, and short-horizon benchmarks that fail to capture…

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Abstract reasoning ability reflects the intelligence and generalization capacity of LLMs to extract and apply abstract rules. However, accurately measuring this ability remains challenging: existing benchmarks either rely on expensive…

Supervised fine-tuning (SFT) has emerged as one of the most effective ways to improve the performance of large language models (LLMs) in downstream tasks. However, SFT can have difficulty generalizing when the underlying data distribution…

Can transformers learn to perform algorithmic tasks reliably across previously unseen input/output domains? While pre-trained language models show solid accuracy on benchmarks incorporating algorithmic reasoning, assessing the reliability…

We introduce a simple, yet novel entropy-based framework to drive token efficiency in large language models during reasoning tasks. Our approach uses Shannon entropy from token-level logprobs as a confidence signal to enable early stopping,…