Running on Zero Agents Dialectical Abstracts 👀 Generate a research paper abstract from chosen intuitions
Running on Zero Agents Dialectical Abstracts 👀 Generate a research paper abstract from chosen intuitions
Running on Zero Agents Dialectical Intuitions 🤔 Judge intuitions; Qwen3-8B writes the view behind them
Running on Zero Agents Dialectical Intuitions 🤔 Judge intuitions; Qwen3-8B writes the view behind them
Sleeping Agents Dialectical Transition Operator v2 🔁 Iterative answer+critique self-improvement (graded RL)
Sleeping Agents Dialectical Transition Operator v2 🔁 Iterative answer+critique self-improvement (graded RL)
Sleeping Agents Dialectical Transition Operator 🔁 Iterative answer + critique self-improvement (Qwen3-8B, RL)
Sleeping Agents Dialectical Transition Operator 🔁 Iterative answer + critique self-improvement (Qwen3-8B, RL)
Sleeping Agents Dialectical LLM — Qwen3-32B positions-only RL 🌿 Qwen3-32B positions-only RL — distinct answers, no counters
Sleeping Agents Dialectical LLM — Qwen3-32B positions-only RL 🌿 Qwen3-32B positions-only RL — distinct answers, no counters
Sleeping Agents Dialectical LLM — Qwen3-32B SFT 🌳 Qwen3-32B (SFT) — distinct positions + counters as a tree
Sleeping Agents Dialectical LLM — Qwen3-32B SFT 🌳 Qwen3-32B (SFT) — distinct positions + counters as a tree