每天自动聚合 AI 领域最新动态
Chain-of-thought (CoT) reasoning is the dominant paradigm for inference-time scaling in language models, yet the caus...
Dispatch in three-sided marketplaces provides a natural setting for reinforcement learning from world feedback: decis...
When large language models (LLMs) fail to generalize or make haphazard errors in reasoning, it is often taken as evid...
Agent systems are advancing quickly across domains, but their evaluation remains fragmented. Most benchmarks rely on ...
Search-augmented LLMs increasingly mediate everyday consumer recommendations by retrieving live web content. This cre...
Shielded reinforcement learning is typically presented as a runtime safety mechanism that compiles temporal-logic spe...
There is a proliferation of work arguing for the use of synthetic data in scientific research. For example, social sc...
We introduce SkMTEB, the first comprehensive MTEB-style text embedding benchmark for Slovak, a low-resource West Slav...
This paper examines three recent frameworks for understanding the cognitive and epistemic consequences of artificial ...
LLM-based agents have shown increasing potential in automating scientific discovery. Given an optimizable metric and ...
Current LLM-based research agents have advanced through agent orchestration, yet largely overlook scientific knowledg...
Reproducibility in the social and behavioral sciences is typically evaluated by independent researchers who reanalyze...