The Flow has not summarised this story yet — read it at arXiv Computation and Language.
WordPolo is a word‑finding task that evaluates language models by having them guess an unknown target word and receive semantic similarity feedback. Participants start with no knowledge, make iterative guesses, and receive distance scores that guide them through semantic space. The study tests recent LLMs, LRMs, humans, and a heuristic on 1,500 puzzles, revealing that while solve rates vary widely, many models make meaningful progress and exhibit human‑like strategies, highlighting the importance of assessing reasoning processes, not just final accuracy.
arXiv:2607. 20520v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated on mathematical problem solving, yet prior work often treats representationally equivalent formulations as interchangeable and conflates reasoning errors with interface failures.
arXiv:2608. 12391v1 Announce Type: cross Abstract: Graph reasoning provides a promising testbed for evaluating the reasoning ability of large language models (LLMs), as graph instances can be programmatically generated, structurally controlled, and naturally scaled to long-input settings.
arXiv:2602.00377v3 Announce Type: replace Abstract: Existing knowledge probing methods rely on pre-defined queries, limiting extraction to known concepts. We introduce DecompressionLM, a stateless fr...
SyntaxBench is a diagnostic benchmark and statistical evaluation framework for character‑level reasoning in large language models, comprising five core tasks—character counting, letter containment, palindrome detection, edit distance, and longest‑string selection—and a harder substring‑extraction stress test called index_to_span. The benchmark uses paired English and random‑string inputs, zero‑, one‑, and four‑shot prompts, and evaluates models from 2B to 32B parameters across multiple reasoning modes. It reports a wide range of metrics, including exact‑match and relaxed accuracy, Cohen’s kappa, McNemar tests, bootstrap confidence intervals, Kendall’s tau, class‑conditional metrics, tokenization analysis, and multiple‑comparison‑corrected tests.
arXiv:2609.25001v1 Announce Type: new Abstract: Modern video games provide a measurable testbed for AI models, combining abilities of visual understanding, instruction decomposition, goal planning, a...