Think-at-Hard selectively triggers latent iterations only on hard tokens via a neural decider and depth-aware LoRA, yielding 3.8-6.8% gains over baselines on nine reasoning benchmarks while iterating on just 7% of tokens.
think-twice
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Effective Feedback Compute (EFC) and its variants provide a superior scaling coordinate for agent harnesses, achieving R² up to 0.99 versus near-zero for raw compute, while enabling higher pass rates at lower cost.
Large-scale experiments on two million agents reveal that collective intelligence does not emerge from scale alone due to sparse and shallow interactions.
citing papers explorer
-
Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
Think-at-Hard selectively triggers latent iterations only on hard tokens via a neural decider and depth-aware LoRA, yielding 3.8-6.8% gains over baselines on nine reasoning benchmarks while iterating on just 7% of tokens.
-
Scaling Laws for Agent Harnesses via Effective Feedback Compute
Effective Feedback Compute (EFC) and its variants provide a superior scaling coordinate for agent harnesses, achieving R² up to 0.99 versus near-zero for raw compute, while enabling higher pass rates at lower cost.
-
Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents
Large-scale experiments on two million agents reveal that collective intelligence does not emerge from scale alone due to sparse and shallow interactions.