LLM reasoning / chain-of-thought
Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here
1 papers critique it · 0 beat it on benchmarks
Verbatim critique sentences, each from a paper that cites pruning-based CoT refinement as a baseline.
merely pruning redundant or erroneous steps does not ensure accurate knowledge usage in the core thought
Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.