LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents
Paper • 2611.02332 • Published • 7
Debargha
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
Debargha
submitted a
paper to Daily Papers about 5 hours ago
optimusPrimeBee
authored a
paper 2 days ago
Debargha
submitted a
paper to Daily Papers 4 days ago
Debargha
submitted a
paper to Daily Papers 28 days ago
Debargha
authored 5
papers about 2 months ago
Beyond Solver Verdicts: Generative Reward Models for Autoformalization
Paper • 2609.11085 • Published • 12
StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean
Paper • 2609.09264 • Published • 9
Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility
Paper • 2608.04001 • Published • 1
Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
Paper • 2601.07036 • Published
Trust The Typical
Paper • 2602.04581 • Published • 2
optimusPrimeBee
authored 7
papers about 2 months ago
Beyond Solver Verdicts: Generative Reward Models for Autoformalization
Paper • 2609.11085 • Published • 12
StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean
Paper • 2609.09264 • Published • 9
Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility
Paper • 2608.04001 • Published • 1
Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models
Paper • 2605.11459 • Published
HugRAG: Hierarchical Causal Knowledge Graph Design for RAG
Paper • 2602.05143 • Published
Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
Paper • 2601.07036 • Published
Trust The Typical
Paper • 2602.04581 • Published • 2
optimusPrimeBee
submitted a
paper to Daily Papers about 2 months ago
Debargha
submitted a
paper to Daily Papers about 2 months ago
Debargha
submitted a
paper to Daily Papers 9 months ago
optimusPrimeBee
authored a
paper 9 months ago