Copertina

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ramesh, Shyam Sundhar, Ji, Xiaotong, Zimmer, Matthieu, Yoon, Sangwoong, Wang, Zhiyong, Ammar, Haitham Bou, Lucchi, Aurelien, Bogunovic, Ilija
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

On Almost Surely Safe Alignment of Large Language Models at Inference-Time
di: Ji, Xiaotong, et al.
Pubblicazione: (2025)

Group Robust Preference Optimization in Reward-free RLHF
di: Ramesh, Shyam Sundhar, et al.
Pubblicazione: (2024)

Robust Multi-Objective Controlled Decoding of Large Language Models
di: Son, Seongho, et al.
Pubblicazione: (2025)

This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs
di: Wolf, Lorenz, et al.
Pubblicazione: (2025)

Risk-Controlled Lean-as-Judge for Natural-Language Mathematical Reasoning
di: Bourigault, Pauline, et al.
Pubblicazione: (2026)

Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening
di: Ji, Xiaotong, et al.
Pubblicazione: (2026)

Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers
di: Ji, Xiaotong, et al.
Pubblicazione: (2026)

Rethinking Large Language Model Distillation: A Constrained Markov Decision Process Perspective
di: Zimmer, Matthieu, et al.
Pubblicazione: (2025)

wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models
di: Tang, Xiaohang, et al.
Pubblicazione: (2025)

Mixture of Attentions For Speculative Decoding
di: Zimmer, Matthieu, et al.
Pubblicazione: (2024)

The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling
di: Nguyen, Tu, et al.
Pubblicazione: (2026)

The $\mathbf{Y}$-Combinator for LLMs: Solving Long-Context Rot with $λ$-Calculus
di: Roy, Amartya, et al.
Pubblicazione: (2026)

LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs?
di: Ziomek, Juliusz, et al.
Pubblicazione: (2026)

Distributionally Robust Model-based Reinforcement Learning with Large State Spaces
di: Ramesh, Shyam Sundhar, et al.
Pubblicazione: (2023)

Bourbaki: Self-Generated and Goal-Conditioned MDPs for Theorem Proving
di: Zimmer, Matthieu, et al.
Pubblicazione: (2025)

Many of Your DPOs are Secretly One: Attempting Unification Through Mutual Information
di: Tutnov, Rasul, et al.
Pubblicazione: (2025)

A Pragmatist Robot: Learning to Plan Tasks by Experiencing the Real World
di: Qu, Kaixian, et al.
Pubblicazione: (2025)

Overton Pluralistic Reinforcement Learning for Large Language Models
di: Fu, Yu, et al.
Pubblicazione: (2026)

RSPO: Regularized Self-Play Alignment of Large Language Models
di: Tang, Xiaohang, et al.
Pubblicazione: (2025)

Why Can Large Language Models Generate Correct Chain-of-Thoughts?
di: Tutunov, Rasul, et al.
Pubblicazione: (2023)

GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models
di: Tang, Xiaohang, et al.
Pubblicazione: (2026)

SuRe: Surprise-Driven Prioritised Replay for Continual LLM Learning
di: Hazard, Hugo, et al.
Pubblicazione: (2025)

SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks
di: Christopoulou, Fenia, et al.
Pubblicazione: (2024)

Subjective Depth and Timescale Transformers: Learning Where and When to Compute
di: Wieser, Frederico, et al.
Pubblicazione: (2025)

Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks
di: Yang, Yuqing, et al.
Pubblicazione: (2026)

Untangling Component Imbalance in Hybrid Linear Attention Conversion Methods
di: Benfeghoul, Martin, et al.
Pubblicazione: (2025)

Reliable LLM-based User Simulator for Task-Oriented Dialogue Systems
di: Sekulić, Ivan, et al.
Pubblicazione: (2024)

LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoning
di: Zhu, Yu, et al.
Pubblicazione: (2026)

DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning
di: Chen, Xiwen, et al.
Pubblicazione: (2025)

Al-Khwarizmi: Discovering Physical Laws with Foundation Models
di: Mower, Christopher E., et al.
Pubblicazione: (2025)

Tree-OPO: Off-policy Monte Carlo Tree-Guided Advantage Optimization for Multistep Reasoning
di: Huang, Bingning, et al.
Pubblicazione: (2025)

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback
di: Zhang, Xiaoying, et al.
Pubblicazione: (2025)

Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning
di: Oomerjee, Adnan, et al.
Pubblicazione: (2025)

LLM for Complex Reasoning Task: An Exploratory Study in Fermi Problems
di: Liu, Zishuo, et al.
Pubblicazione: (2025)

Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks
di: Yugeswardeenoo, Dharunish, et al.
Pubblicazione: (2024)

TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation
di: Wang, Yaoxiang, et al.
Pubblicazione: (2024)

Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks
di: Guan, Jiannan, et al.
Pubblicazione: (2025)

Beyond Memorization: Testing LLM Reasoning on Unseen Theory of Computation Tasks
di: Shelat, Shlok, et al.
Pubblicazione: (2026)

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
di: Dai, Yanqi, et al.
Pubblicazione: (2026)

SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types
di: Mou, Yutao, et al.
Pubblicazione: (2024)