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.
Multi-task grpo: Reliable llm reasoning across tasks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
baseline 1polarities
baseline 1representative citing papers
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
-
Target Policy Optimization
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.
-
M2A: Synergizing Mathematical and Agentic Reasoning in Large Language 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.