pith. sign in

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

fields

cs.AI 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

roles

baseline 1

polarities

baseline 1

representative citing papers

Target Policy Optimization

cs.LG · 2026-04-07 · unverdicted · novelty 6.0

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.

citing papers explorer

Showing 2 of 2 citing papers.

  • Target Policy Optimization cs.LG · 2026-04-07 · unverdicted · none · ref 12

    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 cs.AI · 2026-05-11 · unverdicted · none · ref 28

    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.