Copertina

VinePPO: Refining Credit Assignment in RL Training of LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kazemnejad, Amirhossein, Aghajohari, Milad, Portelance, Eva, Sordoni, Alessandro, Reddy, Siva, Courville, Aaron, Roux, Nicolas Le
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning
di: Aghajohari, Milad, et al.
Pubblicazione: (2025)

Exploiting Tree Structure for Credit Assignment in RL Training of LLMs
di: Tran, Hieu, et al.
Pubblicazione: (2025)

Reframing linguistic bootstrapping as joint inference using visually-grounded grammar induction models
di: Portelance, Eva, et al.
Pubblicazione: (2024)

V-STaR: Training Verifiers for Self-Taught Reasoners
di: Hosseini, Arian, et al.
Pubblicazione: (2024)

Improving Context-Aware Preference Modeling for Language Models
di: Pitis, Silviu, et al.
Pubblicazione: (2024)

LOQA: Learning with Opponent Q-Learning Awareness
di: Aghajohari, Milad, et al.
Pubblicazione: (2024)

Towards Modular LLMs by Building and Reusing a Library of LoRAs
di: Ostapenko, Oleksiy, et al.
Pubblicazione: (2024)

On the Compatibility of Generative AI and Generative Linguistics
di: Portelance, Eva, et al.
Pubblicazione: (2024)

DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning
di: Marjanović, Sara Vera, et al.
Pubblicazione: (2025)

Best Response Shaping
di: Aghajohari, Milad, et al.
Pubblicazione: (2024)

Learning Robust Social Strategies with Large Language Models
di: Piche, Dereck, et al.
Pubblicazione: (2025)

APEX-Searcher: Refining Credit Assignment with Subgoaling for Agentic Retrieval-Augmented Generation
di: Chen, Kun, et al.
Pubblicazione: (2026)

Scaling Graph-Based Dependency Parsing with Arc Vectorization and Attention-Based Refinement
di: Floquet, Nicolas, et al.
Pubblicazione: (2025)

AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
di: Lù, Xing Han, et al.
Pubblicazione: (2025)

Learning the meanings of function words from grounded language using a visual question answering model
di: Portelance, Eva, et al.
Pubblicazione: (2023)

Not All LLM Reasoners Are Created Equal
di: Hosseini, Arian, et al.
Pubblicazione: (2024)

Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
di: Guo, Yiran, et al.
Pubblicazione: (2025)

Beyond Uniform Credit: Causal Credit Assignment for Policy Optimization
di: Khandoga, Mykola, et al.
Pubblicazione: (2026)

Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
di: Noukhovitch, Michael, et al.
Pubblicazione: (2024)

Advantage Alignment Algorithms
di: Duque, Juan Agustin, et al.
Pubblicazione: (2024)

Forecasting Downstream Performance of LLMs With Proxy Metrics
di: Patel, Arkil, et al.
Pubblicazione: (2026)

Dependent Type Refinements for Futures
di: Somayyajula, Siva, et al.
Pubblicazione: (2023)

The Promise of RL for Autoregressive Image Editing
di: Ahmadi, Saba, et al.
Pubblicazione: (2025)

Effect of Document Packing on the Latent Multi-Hop Reasoning Capabilities of Large Language Models
di: Prato, Gabriele, et al.
Pubblicazione: (2025)

Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL
di: Hong, Joey, et al.
Pubblicazione: (2025)

From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models
di: Zhang, Chenchen
Pubblicazione: (2026)

Reducing Credit Assignment Variance via Counterfactual Reasoning Paths
di: Ding, Fei, et al.
Pubblicazione: (2026)

Humans and LLMs Diverge on Probabilistic Inferences
di: Kamath, Gaurav, et al.
Pubblicazione: (2026)

How to Get Your LLM to Generate Challenging Problems for Evaluation
di: Patel, Arkil, et al.
Pubblicazione: (2025)

Investigating Adversarial Trigger Transfer in Large Language Models
di: Meade, Nicholas, et al.
Pubblicazione: (2024)

Not All Data Are Unlearned Equally
di: Krishnan, Aravind, et al.
Pubblicazione: (2025)

Learning Action and Reasoning-Centric Image Editing from Videos and Simulations
di: Krojer, Benno, et al.
Pubblicazione: (2024)

Advancing Language Multi-Agent Learning with Credit Re-Assignment for Interactive Environment Generalization
di: He, Zhitao, et al.
Pubblicazione: (2025)

Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQL
di: Dai, Yaxun, et al.
Pubblicazione: (2026)

Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use
di: Kumar, Abhijit, et al.
Pubblicazione: (2026)

Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning
di: Li, Ziheng, et al.
Pubblicazione: (2026)

InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning
di: Yang, Matthew Y. R., et al.
Pubblicazione: (2026)

CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment
di: Xie, Guofu, et al.
Pubblicazione: (2025)

Exploration Hacking: Can LLMs Learn to Resist RL Training?
di: Jang, Eyon, et al.
Pubblicazione: (2026)

CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic
di: Zhang, Yaocheng, et al.
Pubblicazione: (2025)