IG-Search computes step-level information gain rewards from policy probabilities to improve credit assignment in RL training for search-augmented QA, yielding 1.6-point gains over trajectory-level baselines on multi-hop tasks.
Treegrpo: Tree-advantage grpo for online rl post-training of diffusion models.arXiv preprint arXiv:2512.08153
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 3
other 1
citation-polarity summary
years
2026 10representative citing papers
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
Super-Linear Advantage Shaping (SLAS) introduces a non-linear geometric policy update for RL post-training of text-to-image models that reshapes the local policy space via advantage-dependent Fisher-Rao weighting to reduce reward hacking and improve performance over GRPO baselines.
A learned orchestration policy for LLM agents that jointly optimizes task decomposition and selective routing to (model, primitive) pairs, delivering 77% macro pass@1 at 10x lower cost than strong baselines across 13 benchmarks.
Sol-RL decouples FP4-based candidate exploration from BF16 policy optimization in diffusion RL, delivering up to 4.64x faster convergence with maintained or superior alignment performance on models like FLUX.1 and SD3.5.
Precise is a new SDE-consistent stochastic sampler that balances exploration and stability for RL post-training of flow-matching models via a novel posterior-mean approximation.
E3-TIR integrates expert prefixes, guided branches, and self-exploration via mix policy optimization to deliver 6% better tool-use performance with under 10% of the usual synthetic data and 1.46x ROI.
R²-Searcher introduces fine-grained evidence modeling, retrieval reflection, and R²PO RL to calibrate retrieval-reasoning boundaries and improve multi-hop QA performance.
citing papers explorer
-
IG-Search: Step-Level Information Gain Rewards for Search-Augmented Reasoning
IG-Search computes step-level information gain rewards from policy probabilities to improve credit assignment in RL training for search-augmented QA, yielding 1.6-point gains over trajectory-level baselines on multi-hop tasks.
-
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
-
Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping
Super-Linear Advantage Shaping (SLAS) introduces a non-linear geometric policy update for RL post-training of text-to-image models that reshapes the local policy space via advantage-dependent Fisher-Rao weighting to reduce reward hacking and improve performance over GRPO baselines.
-
Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation
A learned orchestration policy for LLM agents that jointly optimizes task decomposition and selective routing to (model, primitive) pairs, delivering 77% macro pass@1 at 10x lower cost than strong baselines across 13 benchmarks.
-
FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling
Sol-RL decouples FP4-based candidate exploration from BF16 policy optimization in diffusion RL, delivering up to 4.64x faster convergence with maintained or superior alignment performance on models like FLUX.1 and SD3.5.
-
Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models
Precise is a new SDE-consistent stochastic sampler that balances exploration and stability for RL post-training of flow-matching models via a novel posterior-mean approximation.
-
E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning
E3-TIR integrates expert prefixes, guided branches, and self-exploration via mix policy optimization to deliver 6% better tool-use performance with under 10% of the usual synthetic data and 1.46x ROI.
-
R$^2$-Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search
R²-Searcher introduces fine-grained evidence modeling, retrieval reflection, and R²PO RL to calibrate retrieval-reasoning boundaries and improve multi-hop QA performance.
- Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning
- Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic