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.
Multi-task grpo: Reliable llm reasoning across tasks
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
baseline 1polarities
baseline 1representative citing papers
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.
MedAgentBench-v3 shows capability ceilings and format-knowledge barriers limit pure RL to 18.2% while rule-based SFT reaches 34.1% on clinical protocol tasks.
TPO constructs a target distribution q proportional to the old policy times exp(utility) and trains the policy to match it via cross-entropy, matching or beating PPO and GRPO especially under sparse rewards.
CARE-RL combines PA-GRM for task-adaptive rewards on open-ended tasks and DACSP for modulating RL updates using historical capability directions, reporting higher total average scores than baselines on Qwen models.
M2A uses null-space model merging to combine mathematical and agentic reasoning in LLMs, raising SWE-Bench Verified performance from 44.0% to 51.2% on Qwen3-8B without retraining.
citing papers explorer
-
Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Models
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.