DART is a training-free router that accepts direct answers on draft agreement and allocates thinking budgets via draft entropy on disagreement, reporting accuracy gains and token reductions on math and code benchmarks across model scales.
Pranoy Panda, Raghav Magazine, Chaitanya Devaguptapu, Sho Takemori, and Vishal Sharma
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 8verdicts
UNVERDICTED 8roles
background 1polarities
background 1representative citing papers
SWE-Router introduces trajectory-conditioned value-based routing for LLM agents on SWE tasks, with a Bayes-optimality theorem and empirical cost savings while retaining most strong-model performance.
DLLG learns token-level fusion weights for LLM experts from sparse response supervision and outperforms routing, ensembling, and merging baselines on reasoning and code tasks.
SeqRoute applies offline RL with CQL and Hindsight Budget Relabeling to sequential LLM routing under global budgets, claiming 6.0-73.5% cost reduction, maintained or improved quality, and under 1% bankruptcy rate.
MCPP uses Monte Carlo simulations of workflow executions to dynamically allocate resources and replan, raising constrained completion probability over baselines on CodeFlow and ProofFlow.
A Lagrangian-relaxation plus imitation-learning pipeline adaptively allocates test-time compute to LLMs, outperforming uniform baselines by up to 12.8% relative accuracy on MATH while staying within a fixed average budget.
Introduces a modality-switching mechanism for LLMs on spatial reasoning tasks using a trustworthiness and complexity based metric, showing up to 42% performance improvement.
DARS replaces single-shot response labels with distribution-aware supervision derived from input and output uncertainty to produce more reliable LLM routing policies.
citing papers explorer
-
DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models
DART is a training-free router that accepts direct answers on draft agreement and allocates thinking budgets via draft entropy on disagreement, reporting accuracy gains and token reductions on math and code benchmarks across model scales.
-
SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks
SWE-Router introduces trajectory-conditioned value-based routing for LLM agents on SWE tasks, with a Bayes-optimality theorem and empirical cost savings while retaining most strong-model performance.
-
DLLG: Dynamic Logit-Level Gating of LLM Experts
DLLG learns token-level fusion weights for LLM experts from sparse response supervision and outperforms routing, ensembling, and merging baselines on reasoning and code tasks.
-
SeqRoute: Global Budget-Aware Sequential LLM Routing via Offline Reinforcement Learning
SeqRoute applies offline RL with CQL and Hindsight Budget Relabeling to sequential LLM routing under global budgets, claiming 6.0-73.5% cost reduction, maintained or improved quality, and under 1% bankruptcy rate.
-
On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows
MCPP uses Monte Carlo simulations of workflow executions to dynamically allocate resources and replan, raising constrained completion probability over baselines on CodeFlow and ProofFlow.
-
Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization
A Lagrangian-relaxation plus imitation-learning pipeline adaptively allocates test-time compute to LLMs, outperforming uniform baselines by up to 12.8% relative accuracy on MATH while staying within a fixed average budget.
-
Spatial Reasoning via Modality Switching Between Language and Symbolic Representation
Introduces a modality-switching mechanism for LLMs on spatial reasoning tasks using a trustworthiness and complexity based metric, showing up to 42% performance improvement.
-
From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing
DARS replaces single-shot response labels with distribution-aware supervision derived from input and output uncertainty to produce more reliable LLM routing policies.