F-GRPO factorizes group-relative policy optimization into generation and ranking phases within one autoregressive sequence, using order-invariant coverage and position-aware utility rewards to improve top-ranked performance on recommendation and multi-hop QA tasks.
arXiv preprint arXiv:2504.16420 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 2polarities
background 2representative citing papers
OLIVIA treats LLM agent action selection as a contextual linear bandit over frozen hidden states and applies UCB exploration to adapt online, yielding consistent gains over static ReAct and prompt-based baselines on four benchmarks.
CMIB uses a conditional multimodal information bottleneck to create reusable agent skills that separate verbalizable text content from predictive perceptual residuals, improving execution stability.
Skill-R1 applies bi-level group-relative policy optimization to evolve skills recurrently from verified outcomes, yielding gains over baselines on multi-step tasks.
FLR factorizes latent reasoning into multiple preference factors using multi-factor attention and regularizations, outperforming baselines on recommendation benchmarks while adding robustness and interpretability.
TRU is a plug-and-play unlearning method for multimodal recommenders that applies ranking fusion, modality scaling, and layer isolation to achieve better retain-forget trade-offs than uniform baselines.
citing papers explorer
-
F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking
F-GRPO factorizes group-relative policy optimization into generation and ranking phases within one autoregressive sequence, using order-invariant coverage and position-aware utility rewards to improve top-ranked performance on recommendation and multi-hop QA tasks.
-
OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents
OLIVIA treats LLM agent action selection as a contextual linear bandit over frozen hidden states and applies UCB exploration to adapt online, yielding consistent gains over static ReAct and prompt-based baselines on four benchmarks.
-
Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck
CMIB uses a conditional multimodal information bottleneck to create reusable agent skills that separate verbalizable text content from predictive perceptual residuals, improving execution stability.
-
Skill-R1: Agent Skill Evolution via Reinforcement Learning
Skill-R1 applies bi-level group-relative policy optimization to evolve skills recurrently from verified outcomes, yielding gains over baselines on multi-step tasks.
-
Factorized Latent Reasoning for LLM-based Recommendation
FLR factorizes latent reasoning into multiple preference factors using multi-factor attention and regularizations, outperforming baselines on recommendation benchmarks while adding robustness and interpretability.
-
TRU: Targeted Reverse Update for Efficient Multimodal Recommendation Unlearning
TRU is a plug-and-play unlearning method for multimodal recommenders that applies ranking fusion, modality scaling, and layer isolation to achieve better retain-forget trade-offs than uniform baselines.