TurnOPD improves on-policy distillation for long-horizon agents by adaptively budgeting rollout depth and progressively shifting KL loss from token-level to turn-balanced weighting, achieving up to 2.29x faster training with better accuracy on ALFWorld, WebShop, and Multi-Hop Search.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
A 4B deep research agent trained on 10K open data outperforms prior agents under 9B parameters and narrows the gap to 30B-class systems on research benchmarks.
STARE applies surprisal-guided token-level advantage reweighting plus a target-entropy gate to stabilize entropy in GRPO RL for LLMs, yielding stable training and 4-8% gains on AIME24/25 over baselines.
DuMate-DeepResearch introduces a multi-agent deep research system with graph-based planning, recursive execution, and rubric optimization that reports new state-of-the-art scores of 58.03% and 61.95% on two benchmarks.
citing papers explorer
-
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
TurnOPD improves on-policy distillation for long-horizon agents by adaptively budgeting rollout depth and progressively shifting KL loss from token-level to turn-balanced weighting, achieving up to 2.29x faster training with better accuracy on ALFWorld, WebShop, and Multi-Hop Search.
-
DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data
A 4B deep research agent trained on 10K open data outperforms prior agents under 9B parameters and narrows the gap to 30B-class systems on research benchmarks.
-
STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability
STARE applies surprisal-guided token-level advantage reweighting plus a target-entropy gate to stabilize entropy in GRPO RL for LLMs, yielding stable training and 4-8% gains on AIME24/25 over baselines.
-
DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning
DuMate-DeepResearch introduces a multi-agent deep research system with graph-based planning, recursive execution, and rubric optimization that reports new state-of-the-art scores of 58.03% and 61.95% on two benchmarks.