Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2610.18410v1 Announce Type: cross Abstract: Dense vector retrieval can miss evidence connected through intermediate entities, while direct graph retrieval requires access to the graph at query...
arXiv:2610.17900v1 Announce Type: new Abstract: Extended chain-of-thought reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers wit...
arXiv:2610.16984v1 Announce Type: cross Abstract: Offline reinforcement learning aims to learn effective policies from fixed datasets without environment interaction. Although generative models such...
arXiv:2610.18499v1 Announce Type: cross Abstract: Egocentric video understanding spans diverse capabilities, modalities, and evaluation formats, yet these are often studied in isolation despite their...
arXiv:2610.18603v1 Announce Type: new Abstract: Benchmarks report what an Artificial Intelligence (AI) agent can do on a task suite, but not whether one released version has been engineered with the...
arXiv:2610.19603v1 Announce Type: new Abstract: Transformers have demonstrated strong performance in long-term time series forecasting (LTSF), yet modeling non-stationary temporal dependencies remain...
arXiv:2610.18497v1 Announce Type: new Abstract: Tool-call judges evaluate argument values proposed by LLM agents. We find that they accept a correct value less often when their input holds no referen...
arXiv:2610.18298v1 Announce Type: new Abstract: What binds large language models on auditable, hypothesis-driven decision tasks, where every candidate can be checked against the evidence? On the publ...
arXiv:2610.18606v1 Announce Type: new Abstract: Large language models increasingly tackle tasks that require multi-step reasoning, where errors in intermediate claims can affect the final answer. Sel...
arXiv:2610.17124v1 Announce Type: cross Abstract: Full-duplex spoken language models (FD-SLMs) support simultaneous listening and speaking, but often lag behind half-duplex spoken language models (HD...
arXiv:2610.18684v1 Announce Type: new Abstract: Personal-agent memory has largely focused on learning what users know, prefer, and want. However, knowing the user does not necessarily mean knowing wh...
arXiv:2610.18704v1 Announce Type: new Abstract: In this paper, we propose an extremely efficient, training-free method to extract token-level reward signals directly from an existing deep reward mode...
arXiv:2610.14020v1 Announce Type: cross Abstract: Self-driving laboratories (SDLs) aim to automate the full experimental loop, from scientific decision-making to physical execution. Ideally, AI-gener...
arXiv:2610.18125v1 Announce Type: cross Abstract: Training-free diffusion-based compression methods repurpose the generative priors of a diffusion or a flow model to compress data without retraining...
arXiv:2610.17020v1 Announce Type: cross Abstract: Cybersecurity evaluations of AI agents have focused largely on offense, yet a working exploit does not show that an agent can make software safe. An...
arXiv:2610.20012v1 Announce Type: new Abstract: Chemistry evaluation has moved past multiple-choice probes toward open-ended expert problems, yet the benchmarks that define the current frontier still...
arXiv:2610.20009v1 Announce Type: new Abstract: Scaling self-supervised contrastive reinforcement learning (CRL) to 1000-layer Euclidean neural networks has enabled state-of-the-art goal-reaching per...
arXiv:2610.14025v1 Announce Type: cross Abstract: Activation steering controls large language model behavior by adding a direction to hidden activations during inference. For steering to work well, t...
arXiv:2610.14029v1 Announce Type: cross Abstract: LLM-as-a-judge evaluation commonly aggregates multiple judges' decisions into a majority vote, yet this panel decision process does not guarantee tha...
arXiv:2610.19883v1 Announce Type: new Abstract: The growing interest in behavior foundation models, combined with recent advancements in generative modeling, has led to an appealing recipe for reinfo...