arXiv:2604.10917v1 Announce Type: new
Abstract: Enabling large language models to scale and reliably use hundreds of tools is critical for real-world applications, yet challenging due to the inefficiency and error accumulation inherent in flat tool-ca…
arXiv:2602.01064v2 Announce Type: replace
Abstract: Knowledge distillation has emerged as a pivotal technique for transferring knowledge from stronger large language models (LLMs) to smaller, more efficient models. However, traditional distillation ap…
arXiv:2604.09793v1 Announce Type: new
Abstract: Scientific breakthroughs often emerge from synthesizing prior ideas into novel contributions. While language models (LMs) show promise in scientific discovery, their ability to perform this targeted, lit…
arXiv:2604.10923v1 Announce Type: new
Abstract: While large language model–powered agents can self-evolve by accumulating experience or by dynamically creating new assets (i.e., tools or expert agents), existing frameworks typically treat these two e…
arXiv:2603.23516v2 Announce Type: replace
Abstract: Long-term memory is a cornerstone of human intelligence. Enabling AI to process lifetime-scale information remains a long-standing pursuit in
the field. Due to the constraints of full-attention arc…
arXiv:2604.10022v1 Announce Type: new
Abstract: Weird generalization is a phenomenon in which models fine-tuned on data from a narrow domain (e.g. insecure code) develop surprising traits that manifest even outside that domain (e.g. broad misalignment…
arXiv:2604.07717v2 Announce Type: replace
Abstract: Human immunodeficiency virus (HIV)-related stigma is a critical psychosocial determinant of health for people living with HIV (PLWH), influencing mental health, engagement in care, and treatment outc…
arXiv:2604.04415v2 Announce Type: replace
Abstract: Human understanding of video dynamics is typically grounded in a structured mental representation of entities, actions, and temporal relations, rather than relying solely on immediate deductive reaso…
arXiv:2604.09121v2 Announce Type: replace
Abstract: Recent years have witnessed remarkable progress in automatic speech recognition (ASR), driven by advances in model architectures and large-scale training data. However, two important aspects remain u…
arXiv:2604.10072v1 Announce Type: new
Abstract: Recent advancements in the Generative Reward Model (GRM) have demonstrated its potential to enhance the reasoning abilities of LLMs through Chain-of-Thought (CoT) prompting. Despite these gains, existing…