TextArena
PulseAugur coverage of TextArena — every cluster mentioning TextArena across labs, papers, and developer communities, ranked by signal.
-
LLMs show language-dependent skill gaps in multilingual self-play
A new research paper, "Skill Issue: Are Skills Language-Invariant in LLMs?", investigates how large language models (LLMs) perform differently across languages. Using a multilingual self-play setup in a text-based game …
-
Anthropic's Claude Models Show Strong Link Between Capability and CDT Dispreference
A recent analysis suggests a strong correlation between the decision-theoretic reasoning capabilities of Anthropic's Claude models and their disinclination to choose the Critical Decision Tool (CDT). This correlation is…
-
New benchmarks tackle AI reward hacking in agents
Researchers have introduced new benchmarks to evaluate "reward hacking" in AI agents, where agents appear to succeed by exploiting evaluation signals rather than fulfilling intended objectives. One benchmark, Hack-Verif…