RaR uses aggregated rubric feedback as rewards in on-policy RL, delivering up to 31% relative gains on HealthBench and 7% on GPQA-Diamond versus direct Likert LLM-as-judge baselines.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
DITS replaces Q-value guidance in MCTS with influence scores for synthetic data synthesis in multi-agent LLM training, claiming better efficiency and performance on eight datasets.
A co-evolving proposer-critic RL framework improves GUI grounding accuracy by letting the model critique its own proposals rendered on screenshots.
OctoTools framework reports 9.3% average accuracy gain over GPT-4o across 16 tasks by adding tool cards, planner, and executor to LLMs in a training-free setup.
citing papers explorer
-
Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
RaR uses aggregated rubric feedback as rewards in on-policy RL, delivering up to 31% relative gains on HealthBench and 7% on GPQA-Diamond versus direct Likert LLM-as-judge baselines.
-
Efficient Multi-Agent System Training with Data Influence-Oriented Tree Search
DITS replaces Q-value guidance in MCTS with influence scores for synthetic data synthesis in multi-agent LLM training, claiming better efficiency and performance on eight datasets.
-
Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding
A co-evolving proposer-critic RL framework improves GUI grounding accuracy by letting the model critique its own proposals rendered on screenshots.
-
OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning
OctoTools framework reports 9.3% average accuracy gain over GPT-4o across 16 tasks by adding tool cards, planner, and executor to LLMs in a training-free setup.
- Process Supervision of Confidence Margin for Calibrated LLM Reasoning