https://hackerpaper.kaipfister.de/p/2606.01770/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=50324771urn:hackerpapers:mention:2606.01770:50324771Sun, 01 Nov 2026 11:54:10 GMT<p>&gt; Five small models solve a programming problem together: a planner, two ideators, a solver and a manager, plus a repair worker. Each starts from a fresh context and talks only through files on disk. This seems to tie back to the paper Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams[0]. In the Emory paper: &gt; We reduce this loss by expanding Φ with a stateful four-phase multi-agent evolver, temporal-reveal feedback, and cross-cycle memory. This design targets the unbounded-stream failure where a single-agent evolver must absorb growing…</p><p><a href="https://hackerpaper.kaipfister.de/p/2606.01770/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG