Sleeping Agents Critique Autocomplete (ZeroGPU) ๐ฌ gpt-oss-120b on ZeroGPU; reply box prefilled with a critique
Sleeping Agents Critique Autocomplete (ZeroGPU) ๐ฌ gpt-oss-120b on ZeroGPU; reply box prefilled with a critique
Paused Agents Dialectical Transition Operator v2 ๐ Iterative answer+critique self-improvement (graded RL)
Paused Agents Dialectical Transition Operator v2 ๐ Iterative answer+critique self-improvement (graded RL)
Paused Agents Dialectical Transition Operator ๐ Iterative answer + critique self-improvement (Qwen3-8B, RL)
Paused Agents Dialectical Transition Operator ๐ Iterative answer + critique self-improvement (Qwen3-8B, RL)
Paused Agents Dialectical LLM โ Qwen3-32B positions-only RL ๐ฟ Qwen3-32B positions-only RL โ distinct answers, no counters
Paused Agents Dialectical LLM โ Qwen3-32B positions-only RL ๐ฟ Qwen3-32B positions-only RL โ distinct answers, no counters
Paused Agents Dialectical LLM โ Qwen3-32B SFT ๐ณ Qwen3-32B (SFT) โ distinct positions + counters as a tree
Paused Agents Dialectical LLM โ Qwen3-32B SFT ๐ณ Qwen3-32B (SFT) โ distinct positions + counters as a tree