TRL extends tandem training to RLVR pipelines, matching GRPO solo reasoning on Qwen3-4B math tasks while improving handoff robustness, reducing distributional drift, and increasing CoT legibility for the junior.
Sparse but critical: A token-level analysis of distributional shifts in rlvr fine-tuning of llms
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 10verdicts
UNVERDICTED 10roles
method 1polarities
use method 1representative citing papers
ARCA assigns token credit in LoRA-based LLM RL from the norm of adapter-induced hidden state changes, yielding non-degenerate distributions and competitive performance on MATH tasks with Qwen3-1.7B under GRPO.
Temporal scheduling of credit allocation criteria over RLVR training, using trajectory percentiles to target heterogeneous behaviors, yields more stable policy entropy and better reasoning benchmark results than static allocation.
RLRT augments GRPO by reinforcing tokens on correct student rollouts that the teacher would not have predicted, outperforming standard self-distillation and exploration baselines on Qwen3 models.
Attention entropy splits RL training tokens into stable anchors and volatile explorers, and entropy-aware reweighting improves held-out reasoning performance.
APPO refines branching and credit assignment in agentic RL via a Branching Score and procedure-level scaling, improving baselines by nearly 4 points on 13 benchmarks.
DelTA estimates token coefficients to amplify discriminative directions in token-gradient vectors, reweighting the RLVR surrogate to produce more contrastive side-wise centroids and yielding 3.26 and 2.62 point gains on math benchmarks for 8B and 14B Qwen3 models.
ParaVT introduces the first multi-agent RL framework for parallel video tool calling in LMMs, using PARA-GRPO to resolve the Tool Prior Paradox and achieve +7.9% average improvement over Qwen3-VL baseline across six benchmarks.
Proposes Near-boundary Stochastic Rescue (NSR) as a stochastic modification to clipping in RLVR that recovers near-boundary signals and yields gains over baselines like DAPO and GSPO.
OWPO decouples optimization direction from magnitude via asymmetric reweighting (Accelerated Alignment for inferior deviations, Gain Locking for superior) plus iterative references to create a ratchet effect for continuous LLM improvement.
citing papers explorer
No citing papers match the current filters.