Oct 7, 2026 · Artificial Intelligence

VisInteract: Recovering User Intent in Text-to-Vis via Interactive MCTS Search

VisInteract introduces a dynamic interactive Text-to-Vis paradigm with the VisInteract-Bench benchmark and Vis-MCTS method, using Monte Carlo Tree Search with progressive widening, cross-path memory, and dimension-aware reward decomposition to recover user intent from imperfect queries, achieving 51–57% Merge Task Score on 1,098 samples across 11 databases.

Imperfect QueriesInteractive VisualizationMonte Carlo Tree Search

0 likes · 18 min read

VisInteract: Recovering User Intent in Text-to-Vis via Interactive MCTS Search

Machine Heart

Oct 7, 2026 · Artificial Intelligence

SAGE: Topological Guidance Mitigates Long-Horizon Reasoning Biases, 8x Lean Pass Rate

Researchers from Virginia Tech, UW-Madison, and Dartmouth introduce SAGE, a post-training method that uses symbolic closure analysis to diagnose exploration and accumulation biases in long-horizon reasoning, applying algebraic sparsification and hyperbolic structure guidance to improve sampling and provide early feedback, achieving near 8x Lean verification pass rate on Andrews-Curtis tasks and outperforming baselines across 12 benchmarks.

Andrews-CurtisLean VerificationLong-Horizon Reasoning

0 likes · 14 min read

SAGE: Topological Guidance Mitigates Long-Horizon Reasoning Biases, 8x Lean Pass Rate

NeurIPS 2026

VisInteract: Recovering User Intent in Text-to-Vis via Interactive MCTS Search

SAGE: Topological Guidance Mitigates Long-Horizon Reasoning Biases, 8x Lean Pass Rate