Quality follows upgrading
Ever a pioneer, ever a student — learning through our mistakes and failures
전체 전문분석자료
arXiv:2602.16814v1 Announce Type: new Abstract: The expansion of AI toward the edge increasingly exposes the cost and fragility of cen- tralised intelligence. Data transmission, latency, …
arXiv:2602.16827v1 Announce Type: new Abstract: Traditional scoring approaches on hesitant fuzzy sets often lack a formal base in order theory. This paper proposes a unified …
arXiv:2602.16832v1 Announce Type: new Abstract: Safety alignment of large language models (LLMs) is mostly evaluated in English and contract-bound, leaving multilingual vulnerabilities understudied. We introduce …
arXiv:2602.16891v1 Announce Type: new Abstract: Agent development kits (ADKs) provide effective platforms and tooling for constructing agents, and their designs are critical to the constructed …
arXiv:2602.16901v1 Announce Type: new Abstract: LLM agents are increasingly deployed in long-horizon, complex environments to solve challenging problems, but this expansion exposes them to long-horizon …
arXiv:2602.16902v1 Announce Type: new Abstract: We introduce LLM-Wikirace, a benchmark for evaluating planning, reasoning, and world knowledge in large language models (LLMs). In LLM-Wikirace, models …
arXiv:2602.16931v1 Announce Type: new Abstract: Lifelong multimodal agents must continuously adapt to new tasks through post-training, but this creates fundamental tension between acquiring capabilities and …
arXiv:2602.16935v1 Announce Type: new Abstract: While Large Language Model (LLM) capabilities have scaled, safety guardrails remain largely stateless, treating multi-turn dialogues as a series of …
arXiv:2602.16942v1 Announce Type: new Abstract: Large language models (LLMs) increasingly answer queries by citing web sources, but existing evaluations emphasize answer correctness rather than evidence …
arXiv:2602.16943v1 Announce Type: new Abstract: Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs …
arXiv:2602.16953v1 Announce Type: new Abstract: Execution-aware LLM agents offer a promising paradigm for learning from tool feedback, but such feedback is often expensive and slow …
arXiv:2602.16958v1 Announce Type: new Abstract: Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate …