MOPD improves on-policy distillation for LLMs by using peer successes for positive patterns and failures for negative examples to create more informative teacher signals.
hub
Deepmath-103k: A large-scale, challenging, de- contaminated, and verifiable mathematical dataset for advancing reasoning
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
years
2026 17verdicts
UNVERDICTED 17representative citing papers
OPHSD uses harness-augmented models as teachers to distill reasoning capabilities into base LLMs, yielding strong standalone performance on classification and math tasks.
AOPD modifies on-policy distillation by using localized divergence minimization for non-positive advantages instead of negative reinforcement, yielding average gains of 4.09/8.34 over standard OPD on math reasoning benchmarks under strong/weak initialization.
EqLen is a sample-construction framework that builds equal-length paired segments via dual-track generation and masking for stable group-relative RL in sequences, reframing the length problem as a comparison-unit issue rather than loss scaling.
BET reduces reasoning tokens by about 55% on average while improving performance across benchmarks by learning to short-solve easy queries, fold early on unsolvable ones, and preserve budget for hard solvable queries.
DARE co-evolves difficulty estimation and policy in RL for LLMs to improve training efficiency, final performance, and inference speed by using tailored strategies for different difficulty levels.
OPT-BENCH trains LLMs on NP-hard optimization via quality-aware RLVR, achieving 93.1% success rate and 46.6% quality ratio on Qwen2.5-7B while outperforming GPT-4o and transferring gains to other domains.
AIPO trains LLMs to expand their reasoning capability boundary via active multi-agent interaction with Verify, Knowledge, and Reasoning agents during RLVR, using importance sampling and clipping to handle feedback, then drops the agents at inference.
LenVM models token-level remaining generation length as a bounded discounted value function derived from constant negative per-token rewards, providing a scalable proxy for generation horizon.
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.
A new RL paradigm for reasoning where models generate their own internal process supervision from outcome feedback by recycling failed trajectories.
Pion is an optimizer that preserves the singular values of weight matrices in LLM training by applying orthogonal equivalence transformations.
Mid-training LLMs on self-generated diverse reasoning paths improves subsequent RL performance on mathematical benchmarks and OOD tasks.
RLVR exhibits implicit reward overfitting to training data and optimizes heavy-tailed singular spectra with rank-1 focus on reasoning capability.
Mixed-complexity procedural datasets provide up to 5x sample efficiency for RLVR on small models in low-data regimes, with low-to-high complexity generalization observed across counting, graph, and spatial tasks.
PubSwap uses a small public dataset for selective off-policy response swapping in federated RLVR to improve coordination and performance over standard baselines on math and medical reasoning tasks.
The optimal reasoning strategy for LLMs depends on the model's diversity profile rather than the exploration method itself.
citing papers explorer
-
Multi-Rollout On-Policy Distillation via Peer Successes and Failures
MOPD improves on-policy distillation for LLMs by using peer successes for positive patterns and failures for negative examples to create more informative teacher signals.
-
Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning
OPHSD uses harness-augmented models as teachers to distill reasoning capabilities into base LLMs, yielding strong standalone performance on classification and math tasks.
-
Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
AOPD modifies on-policy distillation by using localized divergence minimization for non-positive advantages instead of negative reinforcement, yielding average gains of 4.09/8.34 over standard OPD on math reasoning benchmarks under strong/weak initialization.
-
Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction
EqLen is a sample-construction framework that builds equal-length paired segments via dual-track generation and masking for stable group-relative RL in sequences, reframing the length problem as a comparison-unit issue rather than loss scaling.
-
Nice Fold or Hero Call: Learning Budget-Efficient Thinking for Adaptive Reasoning
BET reduces reasoning tokens by about 55% on average while improving performance across benchmarks by learning to short-solve easy queries, fold early on unsolvable ones, and preserve budget for hard solvable queries.
-
DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation
DARE co-evolves difficulty estimation and policy in RL for LLMs to improve training efficiency, final performance, and inference speed by using tailored strategies for different difficulty levels.
-
Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs
OPT-BENCH trains LLMs on NP-hard optimization via quality-aware RLVR, achieving 93.1% success rate and 46.6% quality ratio on Qwen2.5-7B while outperforming GPT-4o and transferring gains to other domains.
-
AIPO: : Learning to Reason from Active Interaction
AIPO trains LLMs to expand their reasoning capability boundary via active multi-agent interaction with Verify, Knowledge, and Reasoning agents during RLVR, using importance sampling and clipping to handle feedback, then drops the agents at inference.
-
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling
LenVM models token-level remaining generation length as a bounded discounted value function derived from constant negative per-token rewards, providing a scalable proxy for generation horizon.
-
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.
-
Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for Reasoning
A new RL paradigm for reasoning where models generate their own internal process supervision from outcome feedback by recycling failed trajectories.
-
Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation
Pion is an optimizer that preserves the singular values of weight matrices in LLM training by applying orthogonal equivalence transformations.
-
Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models
Mid-training LLMs on self-generated diverse reasoning paths improves subsequent RL performance on mathematical benchmarks and OOD tasks.
-
On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR
RLVR exhibits implicit reward overfitting to training data and optimizes heavy-tailed singular spectra with rank-1 focus on reasoning capability.
-
Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes
Mixed-complexity procedural datasets provide up to 5x sample efficiency for RLVR on small models in low-data regimes, with low-to-high complexity generalization observed across counting, graph, and spatial tasks.
-
PubSwap: Public-Data Off-Policy Coordination for Federated RLVR
PubSwap uses a small public dataset for selective off-policy response swapping in federated RLVR to improve coordination and performance over standard baselines on math and medical reasoning tasks.
-
Your Model Diversity, Not Method, Determines Reasoning Strategy
The optimal reasoning strategy for LLMs depends on the model's diversity profile rather than the exploration method itself.