T-Router: Learning Thalamic Routing for Reasoning with Parameter-Efficient Reinforcement Learning
cs.LG, cs.AI, cs.NE
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/siqi654321/search-agent-rl
Terminology
Sources
- BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
- Training Verifiers to Solve Math Word Problems
- Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL
- Attention Residuals
- Delta Attention Residuals
- Multi-Head Attention Residuals
- Manifold-Constrained Hyper-Connections for Parameter-Efficient Finetuning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Parameter Efficient Reinforcement Learning from Human Feedback
- mHC: Manifold-Constrained Hyper-Connections
- Instruction-Following Evaluation for Large Language Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks