Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2608. 14152v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have reshaped semantic analysis.
arXiv:2608. 14528v1 Announce Type: new Abstract: This study investigates the methodological and theoretical properties of session handover in applications that use large language models.
arXiv:2608. 14021v1 Announce Type: new Abstract: Transformer-based sequential recommenders with causal self-attention often rely heavily on the most recent interaction at inference time, but how this behavior is structurally expressed in the representation used for prediction remains unclear.
arXiv:2608. 13667v1 Announce Type: new Abstract: LLM agents in the ReAct paradigm alternate between reasoning, acting, and observing, but deliberate reasoning is confined to the Thought phase: while the agent serializes an action and waits for the environment, its reasoning is frozen.
arXiv:2608. 13767v1 Announce Type: new Abstract: Analog IC layout design remains a labor-intensive iterative process dominated by simulation-driven refinement.
arXiv:2608. 13608v1 Announce Type: new Abstract: Agentic "Continual Learning Harnesses", systems that pair an LLM with retrieval or memory to improve from feedback without retraining, have shown growing value in cybersecurity.
arXiv:2608. 13617v1 Announce Type: new Abstract: Verifying whether clinical care follows evidence-based protocols is a natural neuro-symbolic problem, yet the safety-critical setting defeats either paradigm alone.
arXiv:2608. 13958v1 Announce Type: new Abstract: How do we govern AI systems whose reasoning we cannot fully inspect?
arXiv:2608. 14036v1 Announce Type: new Abstract: Skills have emerged as a practical and effective approach for enhancing LLM agents at inference time through structured packages of knowledge.
arXiv:2608. 13711v1 Announce Type: cross Abstract: Computer-aided detection (CADe) systems for colonoscopy promise to reduce clinical miss rates, yet reliable real-world deployment remains elusive.
arXiv:2604. 09508v2 Announce Type: replace-cross Abstract: Visual Retrieval-Augmented Generation (VRAG) empowers Vision-Language Models to retrieve and reason over visually rich documents.
arXiv:2608. 13987v1 Announce Type: new Abstract: Nanbeige4.
arXiv:2608. 13598v1 Announce Type: new Abstract: Agent evaluation relies almost entirely on outcome metrics such as success rate, which capture whether an agent succeeds but not how consistently it behaves.
arXiv:2608. 13607v1 Announce Type: new Abstract: Frontier LLMs are updated frequently and typically outperform their predecessors in aggregate.
arXiv:2608. 13605v1 Announce Type: new Abstract: Natural language provides robots with a flexible task interface, but target ambiguity in embodied environments arises not only from user intent; it can also result from missing taskrelevant physical evidence in the current observation.
arXiv:2608. 13573v1 Announce Type: new Abstract: Large Language Model (LLM) serving has become a critical cloud workload, and realistic traces are essential for motivating and benchmarking serving systems.
arXiv:2605. 28642v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have demonstrated significant potential for speech-to-text translation (S2TT).
arXiv:2608. 13566v1 Announce Type: cross Abstract: Post-training papers, model cards, and blog posts often treat scores on a small set of coding benchmarks (e.
arXiv:2608. 13760v1 Announce Type: cross Abstract: Which reasoning behaviors are associated with correct answers in reasoning models, and does reasoning-oriented training amplify those behaviors?
arXiv:2604. 16509v2 Announce Type: replace-cross Abstract: Many robotic exploration algorithms rely on graph structures for frontier-based exploration and dynamic path planning.