Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2608. 04761v1 Announce Type: cross Abstract: Self-improving agents accumulate reusable insights from prior trajectories, making retrieval increasingly important for turning accumulated experience into actionable guidance.
arXiv:2602. 07885v2 Announce Type: replace Abstract: Long-term memory enables large language model agents to tackle complex tasks through historical interactions.
arXiv:2604. 12503v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown remarkable capabilities across various tasks but remain prone to hallucinations in knowledge-intensive scenarios.
arXiv:2605. 27882v2 Announce Type: replace-cross Abstract: LLM-based agents score well on search benchmarks, yet real users consistently find results unsatisfying, revealing a persistent evaluation-experience gap.
arXiv:2608. 04027v1 Announce Type: new Abstract: This work investigates the feasibility of augmenting traditional R-Matrix codes with a robust machine learning framework for automatically detecting neutron resonances in transmission spectra.
arXiv:2608. 05103v1 Announce Type: new Abstract: Data assimilation (DA) uses Bayesian inference to update the state of a numerical forecast model with observed data.
arXiv:2508. 04811v2 Announce Type: replace Abstract: Order dispatch systems play a vital role in ride-hailing services, which directly influence operator revenue, driver profit, and passenger experience.
arXiv:2608. 04677v1 Announce Type: new Abstract: Algorithmic recourse seeks to help individuals reverse unfavorable automated decisions by recommending actionable changes that achieve a desired outcome.
arXiv:2608. 04613v1 Announce Type: new Abstract: Anomaly detection is a safety-critical machine learning problem with applications ranging from fraud detection to network intrusion prevention and industrial monitoring.
arXiv:2608. 04714v1 Announce Type: cross Abstract: Benchmark scores are reported as properties of a model, yet the inference framework used to produce them, such as HuggingFace, vLLM, or Ollama, are considered non-influential and their names and versions are almost never disclosed.
arXiv:2608. 05060v1 Announce Type: cross Abstract: Structured input files such as JSON, DOT, OBJ, INI, S-expression, and TinyC are widely used in software systems, but small corruptions can cause parsers to reject otherwise useful data.
arXiv:2608. 05115v1 Announce Type: cross Abstract: Can computer vision help make classrooms safer?
arXiv:2510. 17640v4 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have shown strong manipulation capability when trained with large-scale imitation learning datasets.
arXiv:2604. 27707v2 Announce Type: replace Abstract: Current agentic memory systems (vector stores, retrieval-augmented generation, scratchpads, and context-window management) do not implement memory: they implement lookup.
arXiv:2602. 06337v2 Announce Type: replace-cross Abstract: Causal inference is essential for decision-making but remains challenging for non-experts.
arXiv:2603. 06140v2 Announce Type: replace-cross Abstract: Video object insertion is fundamental to video editing, yet existing diffusion methods often produce visually plausible but physically inconsistent results.
arXiv:2608. 02392v2 Announce Type: replace-cross Abstract: A wearable assistant should both answer questions about its visual history and recognize when that history is useful to the present situation.
arXiv:2608. 04193v1 Announce Type: cross Abstract: Language models (LMs) offer strong textual representations for electronic health records (EHRs), but they encode patient sequences in isolation and provide limited explainability.
arXiv:2608. 04433v1 Announce Type: cross Abstract: We present MERaLiON-GR, a speech gender recognition system that performs binary classification (female / male) on English and Southeast Asian (SEA) languages.
arXiv:2608. 04756v1 Announce Type: cross Abstract: In Retrieval-Augmented Generation (RAG), post-retrieval conflict resolution arbitrates among noisy or contradictory retrieved passages.