Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2606. 05177v1 Announce Type: cross Abstract: Existing multimodal safety benchmarks focus solely on visual inputs and cannot assess Omni Large Language Models (LLMs) that process vision, audio, and text.
arXiv:2606. 05608v1 Announce Type: cross Abstract: For over half a century, software engineering has operated on a foundational premise: human engineers decompose problems, encode decision logic into static code, and manually adapt that code as requirements evolve.
arXiv:2606. 05986v1 Announce Type: cross Abstract: Existing learning-based detectors for Solidity smart-contracts reduce vulnerability detection to syntactic pattern matching within single functions, yet many of the most consequential exploits (The DAO, Cream Finance) exist not in any individual function but in the relationship between functions and in the combination of conditions that made the attack feasible.
arXiv:2606. 06219v1 Announce Type: cross Abstract: End-to-end autonomous driving models often struggle to balance multi-modal maneuver generation with real-time inference constraints.
arXiv:2602. 13255v2 Announce Type: replace Abstract: We present DPBench, a benchmark for evaluating coordination in multi-agent systems built from large language models.
arXiv:2606. 05855v1 Announce Type: cross Abstract: Continuous electroencephalography (EEG) emotion prediction aims to model the temporal evolution of human emotional states from EEG signals.
arXiv:2606. 06284v1 Announce Type: new Abstract: Large language model agents increasingly rely on external tools, but larger tool menus can reduce reliability and efficiency by increasing wrong-tool calls, premature actions, and token cost.
arXiv:2512. 15231v3 Announce Type: replace Abstract: The automated and intelligent processing of massive remote sensing (RS) datasets is critical in Earth observation (EO).
arXiv:2606. 05924v1 Announce Type: cross Abstract: Literary translation poses unique challenges due to the scarcity of high-quality annotated data and the need to balance expression fluency with literary effect.
arXiv:2606. 05334v1 Announce Type: new Abstract: Returned products in circular factories re-enter production with heterogeneous degradation states, usage histories, and remaining capability.
arXiv:2606. 06261v1 Announce Type: cross Abstract: O-RAN enables a disaggregated baseband stack with programmable functions that communicate over standardized open interfaces.
arXiv:2606. 06217v1 Announce Type: cross Abstract: When a disaster unfolds, responders must answer not only what is happening, but also why it is happening, what will happen next, and what to do now, often from noisy low-altitude UAV views and under tight on-site compute constraints.
arXiv:2510. 11974v2 Announce Type: replace-cross Abstract: Cyber Threat Intelligence (CTI) is foundational to modern cybersecurity, enabling organizations to proactively defend against evolving threats.
arXiv:2606. 05548v1 Announce Type: cross Abstract: The rapid proliferation of Agent Development Kits (ADKs), SDK-level frameworks for building LLM-powered autonomous agents, has outpaced any empirical understanding of how framework choice affects agent performance.
arXiv:2512. 05774v2 Announce Type: replace-cross Abstract: Long video understanding (LVU) is challenging because answering real-world queries often depends on sparse, temporally dispersed cues buried in hours of mostly redundant and irrelevant content.
arXiv:2606. 06462v1 Announce Type: new Abstract: Benchmarks are fundamental for evaluating and advancing LLMs and MLLMs by providing standardized and explicit measures of performance.
arXiv:2606. 06473v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly applied to long-horizon tasks such as scientific discovery and machine learning engineering (MLE), where sustained self-evolution becomes a key capability.
arXiv:2606. 05998v1 Announce Type: cross Abstract: Oral 3D modelling is one of the most essential stages in dentistry, and many different approaches, such as impression taking and intraoral scanning, are commonly used for this phase, each with notable limitations.
arXiv:2606. 05183v1 Announce Type: cross Abstract: Large language models are increasingly deployed as high-stakes advisors, yet standard alignment benchmarks treat sycophancy as a binary failure mode.
arXiv:2606. 05784v1 Announce Type: new Abstract: We identify and formally characterize credit misassignment as a systematic failure mode of GRPO in tool-augmented multimodal search agents: its uniform broadcast of trajectory-level advantages to all tokens causes valuable tool-use steps in failing trajectories to be penalized no differently from valueless ones.