Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models · HackerPapers discussions

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models — mentioned by sva_

Thu, 07 May 2026 13:11:46 GMT

So at the heart of this architecture is what they call 'Markovian RSA', a combination of two papers RSA[0], which generates a certain amount of reasoning traces for a prompt; and the 'Markovian Thinker'[1] which seems to basically cut the end of those traces to keep context at a reasonable length. I feel like there's potential to improve that part of just cutting a tunable amount (τ) of tokens off the tail end of those traces, because you may potentially lose valuable insight earlier in the trace? They did train the model (in SFT) to put the relevant information into the tail (τ) of the…

Paper and discussion history. A mention is not an endorsement.

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models — mentioned by harman2607

Fri, 06 Mar 2026 06:21:17 GMT

Hi HN, I’m one of the authors. This paper studies how LLMs self-verify candidate solutions when doing test-time scaling (parallel reasoning / Best-of-N style generation). We found that models are often much better at pairwise comparisons, where the model scores two solutions (A and B) jointly, than at assigning absolute scores to their own solutions independently. The paper introduces: • Pairwise self-verification instead of pointwise scoring • V1-Infer, a ranking algorithm that selects good candidates efficiently • V1-PairRL, RL training where generation and verification co-evolve to produce…

Paper and discussion history. A mention is not an endorsement.

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models — HN submission

Sat, 04 Oct 2025 12:53:23 GMT

Recursive self-aggregation unlocks deep thinking in large language models

1 point; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.