Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2608. 15619v1 Announce Type: new Abstract: Emotion recognition from text keeps improving on benchmarks, yet whether an accuracy ceiling has been reached is seldom asked with discipline.
arXiv:2608. 15687v1 Announce Type: new Abstract: Sycophancy, the tendency of a language model to change its answer to match a user's stated belief, is a common alignment failure.
arXiv:2608. 15929v1 Announce Type: new Abstract: Pedestrian path prediction is crucial for enhancing the safety of autonomous vehicles and advanced driver-assistance systems.
arXiv:2608. 15956v1 Announce Type: new Abstract: Agentic retrieval workflows produce query, retrieval, and stopping traces as a byproduct of answering questions.
arXiv:2608. 16211v1 Announce Type: new Abstract: Long-horizon agents are beginning to automate complete workflows that produce code, reports, and research artifacts.
arXiv:2608. 16425v1 Announce Type: new Abstract: Parallel reasoning improves the accuracy and robustness of large reasoning models by exploring multiple solution paths, but its computational cost grows with reasoning depth and branch count.
arXiv:2608. 16443v1 Announce Type: new Abstract: Neurosymbolic (NeSy) Artificial Intelligence aims to integrate Deep Learning (DL) architectures with symbolic reasoning.
arXiv:2608. 16637v1 Announce Type: new Abstract: LLMs remain unreliable for long-horizon planning, often generating logically inconsistent or non-applicable plans.
arXiv:2608. 16666v1 Announce Type: new Abstract: This paper presents Chronocooked, a reinforcement learning (RL) benchmark suite for studying implicit interval timing in RL agents.
arXiv:2608. 16763v1 Announce Type: new Abstract: Financial document validation in production, such as payroll auditing, tax compliance, and loan underwriting, demands exceptional accuracy, consistency, and reproducibility under strict enterprise constraints.
arXiv:2608. 14563v1 Announce Type: cross Abstract: Forward-Pass-Only MLP training (FPO) adapts large language models without a backward pass through the model body, achieving 2.
arXiv:2608. 14577v1 Announce Type: cross Abstract: Frontier large language models (LLMs) safety evaluation has largely treated harmful generation as an attack outcome rather than as an object of analysis.
arXiv:2608. 14621v1 Announce Type: cross Abstract: Long-term memory is increasingly central to LLM agents, yet memory design remains a highly coupled architecture problem: what to encode, how to store it, how to retrieve it, and how to manage it can vary substantially across tasks and backbone models.
arXiv:2608. 14653v1 Announce Type: cross Abstract: Prediction uncertainty is a widely adopted metric for quantifying model confidence, with downstream applications spanning model explanation, data selection, and prediction rollback.
arXiv:2608. 14620v1 Announce Type: cross Abstract: Reinforcement Learning (RL) has been extensively used in autonomous and self-* systems, but RL policies, especially deep RL ones relying on neural networks, lack transparency and are difficult to understand.
arXiv:2608. 14728v1 Announce Type: cross Abstract: On-policy distillation (OPD) has emerged as an effective paradigm for transferring knowledge between language models, where a student is trained to align its next-token distribution with the teacher's along its own trajectories.
arXiv:2608. 14741v1 Announce Type: cross Abstract: We introduce PolyComp, a procedurally generated and verified benchmark that stresses visual recognition and compositional spatial reasoning.
arXiv:2608. 14767v1 Announce Type: cross Abstract: Automated vehicles must explain their decisions in ways that passengers can understand, monitor, and trust.
arXiv:2608. 14863v1 Announce Type: cross Abstract: LLM-based coding agents have advanced rapidly on single-process SWE tasks, with frontier models now clustering in the high-70s on SWE-bench Verified.
arXiv:2608. 14922v1 Announce Type: cross Abstract: Mechanistic interpretability has recently expanded to Vision Transformers (ViTs), with Sparse Autoencoders (SAEs) increasingly used as post-hoc tools to decompose internal representations into sparse and more interpretable features.