RL agent for online LHC trigger threshold tuning improves in-tolerance intervals by 28-56% on Monte Carlo and real CMS data without fine-tuning.
super hub Mixed citations
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Mixed citation behavior. Most common role is background (55%).
475
Pith papers citing it
Background
55% of classified citations
abstract
Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning. However, key technical details of state-of-the-art reasoning LLMs are concealed (such as in OpenAI o1 blog and DeepSeek R1 technical report), thus the community still struggles to reproduce their RL training results. We propose the $\textbf{D}$ecoupled Clip and $\textbf{D}$ynamic s$\textbf{A}$mpling $\textbf{P}$olicy $\textbf{O}$ptimization ($\textbf{DAPO}$) algorithm, and fully open-source a state-of-the-art large-scale RL system that achieves 50 points on AIME 2024 using Qwen2.5-32B base model. Unlike previous works that withhold training details, we introduce four key techniques of our algorithm that make large-scale LLM RL a success. In addition, we open-source our training code, which is built on the verl framework, along with a carefully curated and processed dataset. These components of our open-source system enhance reproducibility and support future research in large-scale LLM RL.
hub tools
citation-role summary
background 59
method 26
baseline 11
dataset 10
other 1
citation-polarity summary
claims ledger
- abstract Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning. However, key technical details of state-of-the-art reasoning LLMs are concealed (such as in OpenAI o1 blog and DeepSeek R1 technical report), thus the community still struggles to reproduce their RL training results. We propose the $\textbf{D}$ecoupled Clip and $\textbf{D}$ynamic s$\textbf{A}$mpling $\textbf{P}$olicy $\textbf{O}$ptimization ($\textbf{DAPO}$) algorithm, and fully open-source a state-of-the-art large-scale RL system that achieves 50
authors
co-cited works
representative citing papers
UltraEP is the first exact-load real-time expert balancer for large-EP MoE training and serving on rack-scale nodes, reaching 94.3% of ideal throughput and 1.49x over no-balancing.
ReLibra uses pre-known token-to-expert routing from RL rollouts to perform inter-batch expert reordering and intra-batch replication, delivering up to 1.6x higher throughput than Megatron-LM and 1.2x over oracle-equipped EPLB while staying within 6-10% of an ideal balanced baseline.
EVE enables verifiable self-evolution of MLLMs by using a Challenger-Solver architecture to generate dynamic executable visual transformations that produce VQA problems with absolute execution-verified ground truth.
DeepMath-103K is a new 103K-problem mathematical dataset with high difficulty, rigorous decontamination, and verifiable answers to support RL training of language-model reasoning.
Online IL overcomes an information-theoretic bottleneck that offline IL faces in non-realizable settings even at horizon 1, under a new structural characterization of reward-relative misspecification.
PrincipalBench exposes a sharp split in frontier LLMs between selective and over-refusing behavior on multi-party loyalty, with prompt scaffolding and KL distillation reducing harm rates but only along an existing leak/over-refusal trade-off.
Proposes Monotonic Inference Policy Improvement (MIPI) objective and MIPU two-step update framework to address objective misalignment between training and inference policies in LLM reinforcement learning.
TAC is a bandit curriculum for multi-domain RLVR that prioritizes domains whose gradient updates align with and benefit other domains, yielding up to 2.8-point macro accuracy gains over learnability-only baselines on Qwen3-1.7B and Llama3.2-3B.
OmniOPD replaces token-level logit matching in on-policy distillation with Monte Carlo chunk-level semantic verification and a peak-entropy scheduler.
RL2ML introduces a parameterized family of surrogate objectives bridging RL and ML with unbiased gradient estimators, group-level update-scale analysis, and metric-dependent optimization for finite-rollout LLM training.
Extrapolative weight averaging of RL checkpoints trained under nested unit-test coverage extends a correctness-efficiency frontier and boosts ensemble pass rates in code generation across model scales and inference modes.
Reasoning models naturally compress context via thinking traces, with reward-constrained optimization yielding 17-23% gains over baselines on long-context QA at high compression ratios.
CARL trains a critic for segment-level credit assignment from binary outcomes in LLM tool-use trajectories, yielding 6.7-9.7 point accuracy gains and 53% fewer calls on solvable questions across five benchmarks.
Touch-R1 applies GRPO reinforcement learning on a new 1M tactile dataset and benchmark to train a Qwen2.5-VL-7B model that outperforms baselines on tactile perception and visual-tactile conflict tasks.
ATLAS traces RLVR data to 20 atomic sources, most datasets are variants, and DAPO++ curated with SCA improves RLVR performance while Q predicts training effectiveness.
MCPO applies contrastive learning to GRPO-style RL by treating cross-domain correct rollouts as positives and incorrect ones as negatives to improve multi-domain reasoning performance in LRMs.
CurveRL derives a quantile-coordinate reweighting rule from a utility functional on pass rates and shows it outperforms GRPO on reasoning benchmarks.
ToolMerge decomposes queries into LLM-planned tool calls merged by boolean operators for long-video keyframe retrieval and introduces the M2M benchmark, showing competitive results with 5% gains on caption retrieval.
A reinforcement-learned vision-language agent adaptively selects and fuses monocular depth experts per sample for better performance across camera geometries.
LIFT is a learnability-informed SFT algorithm for diffusion LMs that aligns token difficulty with diffusion time steps, yielding up to 3x gains on AIME'24 and AIME'25 over standard SFT baselines.
Introduces a Cognitive User Simulator modeling stratified personas with hidden concerns and Simulator-Induced Asymmetric-View Policy Optimization to unlock proactive behavior in task-oriented dialogue agents.
MAVEN pipeline generates multi-scale spatio-temporal event descriptions from videos using agentic adaptation and refinement, then produces training data that lets a fine-tuned 8B model outperform Gemini baselines on private CCTV and AccidentBench tasks.
ABS uses Behavioral Divergence to adaptively scale batch sizes in RL according to policy volatility, enabling effective large-batch large-network training on ALE benchmarks.
citing papers explorer
-
Breaking $\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning
GCPO uses team-level credit assignment via determinant volume over reward-weighted semantic embeddings to promote non-redundant correct reasoning paths, improving both accuracy and diversity in LLM training.
-
DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards
DUET improves RLVR by allocating tokens across both prompt selection and rollout length, outperforming full-budget baselines even when using only half the tokens.
-
Seir\^enes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning
Seirênes trains LLMs via adversarial self-play to generate and overcome evolving distractions, producing gains of 7-10 points on math reasoning benchmarks and exposing blind spots in larger models.
-
Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning
METIS internalizes curriculum judgment in LLM reinforcement fine-tuning by predicting within-prompt reward variance via in-context learning and jointly optimizing with a self-judgment reward, yielding superior performance and up to 67% faster convergence across math, code, and agent benchmarks.
-
HTPO: Towards Exploration-Exploitation Balanced Policy Optimization via Hierarchical Token-level Objective Control
HTPO introduces hierarchical token-level objective control in RLVR to balance exploration and exploitation by grouping tokens according to difficulty, correctness, and entropy, yielding up to 8.6% gains on AIME benchmarks over DAPO.
-
Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training
ICR creates a virtual shorter distribution from shortest correct on-policy responses to regularize RL post-training toward concise yet accurate reasoning, improving the accuracy-length Pareto frontier on math and knowledge benchmarks.
-
Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
A parameter-free sampling strategy called CUTS combined with Mixed-CUTS training prevents mode collapse in RL for saturated LLM reasoning tasks and raises AIME25 Pass@1 accuracy by up to 15.1% over standard GRPO.
-
MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation
MAR-GRPO stabilizes GRPO for AR-diffusion hybrids via multi-trajectory expectation and uncertainty-based token selection, yielding better visual quality, stability, and spatial understanding than baselines.
-
VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks
VAPO achieves 60.4 on AIME 2024 with Qwen 32B, outperforming prior methods by over 10 points through targeted fixes for value bias, sequence length variation, and sparse rewards.
-
Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance
FEST improves RLVR sample efficiency on math and coding benchmarks by combining supervised signals, on-policy signals, and decaying weights on just 128 randomly chosen demonstrations, matching full-dataset baselines.
-
JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency
JoyAI-LLM Flash delivers a 48B MoE LLM with 2.7B active parameters per token via FiberPO RL and dense multi-token prediction, released with checkpoints on Hugging Face.