Changing minds beats changing ties: interventions in LLM agent polarization study
profjamesevans · x · 2026-10-09
From the Evans team's paper thread: rewiring networks could not remove polarization; forced cross-cutting contact moved opinions 2%, close to human field experiments; prompting agents to stay open to persuasion cut polarization 11.8%, and neutral influencers cut it 8.8%. In a crystallized network, changing minds beat changing ties. The quoted post frames two implications: emergent polarization may worsen as societies adopt LLM agents, while LLM-based agent models enable unprecedented behavioral interpretability.
More from Research
- Test-Time Structure-Space Search lifts antibody design success from 16% to 78% — anshulkundaje · 2026-10-09
- aimotive driving dataset: train labels come from a tracker that sees the future — RexDouglass · 2026-10-09
- Yale-led study finds symbolic structure inside LLM representations — tallinzen · 2026-10-09
- Discrete Diffusion Meetup at COLM: Oct 8, Grand Ballroom — yuntiandeng · 2026-10-09
- Astra 机器人控制实测:Johns Hopkins 深度评测其运动与控制理解 — jmin__cho · 2026-10-09
- Tavily's 93% live-retrieval agent study challenged: prompts were domain-anchored — edwin · 2026-10-09