Johan Samir Obando Ceron

arxiv.org

Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning

Jiashun Liu

Han Lu

Yancheng He

Weixun Wang

Wenbo Su

Bo Zheng

Aaron Courville

Ling Pan

Most recent RL for LLMs (RL4LLM) methods avoid explicit critics, replacing them with average advantage baselines. This shift is largely prag… (voir plus)matic: conventional value functions are computationally expensive to train at LLM scale and often fail under sparse rewards and long reasoning horizons. We revisit this bottleneck from an architectural perspective and introduce Asymmetric Proximal Policy Optimization (AsyPPO), a simple and scalable framework that restores the critics role while remaining efficient in large-model settings. AsyPPO employs a set of lightweight mini-critics, each trained on disjoint prompt shards. This design encourages diversity while preserving calibration, reducing value-estimation bias. Beyond robust estimation, AsyPPO leverages inter-critic uncertainty to refine the policy update: (i) masking advantages in states where critics agree and gradients add little learning signal, and (ii) filtering high-divergence states from entropy regularization, suppressing spurious exploration. After training on open-source data with only 5,000 samples, AsyPPO consistently improves learning stability and performance across multiple benchmarks over strong baselines, such as GRPO, achieving performance gains of more than six percent on Qwen3-4b-Base and about three percent on Qwen3-8b-Base and Qwen3-14b-Base over classic PPO, without additional tricks. These results highlight the importance of architectural innovations for scalable, efficient algorithms.

2025-10-01

ArXiv (prépublication)

arxiv.org

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models

Yoshua Bengio

Brian R. Bartoldson

Bhavya Kailkhura

Guillaume Lajoie

Glen Berseth

Nikolay Malkin

Moksh J. Jain

Test-time scaling methods improve the capabilities of large language models (LLMs) by increasing the amount of compute used during inference… (voir plus) to make a prediction. Inference-time compute can be scaled in parallel by choosing among multiple independent solutions or sequentially through self-refinement. We propose Recursive Self-Aggregation (RSA), a test-time scaling method inspired by evolutionary methods that combines the benefits of both parallel and sequential scaling. Each step of RSA refines a population of candidate reasoning chains through aggregation of subsets to yield a population of improved solutions, which are then used as the candidate pool for the next iteration. RSA exploits the rich information embedded in the reasoning chains -- not just the final answers -- and enables bootstrapping from partially correct intermediate steps within different chains of thought. Empirically, RSA delivers substantial performance gains with increasing compute budgets across diverse tasks, model families and sizes. Notably, RSA enables Qwen3-4B-Instruct-2507 to achieve competitive performance with larger reasoning models, including DeepSeek-R1 and o3-mini (high), while outperforming purely parallel and sequential scaling strategies across AIME-25, HMMT-25, Reasoning Gym, LiveCodeBench-v6, and SuperGPQA. We further demonstrate that training the model to combine solutions via a novel aggregation-aware reinforcement learning approach yields significant performance gains. Code available at https://github.com/HyperPotatoNeo/RSA.

2025-09-29

ArXiv (prépublication)

arxiv.org

Adaptive Computation Pruning for the Forgetting Transformer

Zhixuan Lin

Xu Owen He

Aaron Courville

The recently proposed Forgetting Transformer (FoX) incorporates a forget gate into softmax attention and has shown consistently better or on… (voir plus)-par performance compared to the standard RoPE-based Transformer. Notably, many attention heads in FoX tend to forget quickly, causing their output at each timestep to rely primarily on local context. Based on this observation, we propose Adaptive Computation Pruning (ACP) for FoX, a method that dynamically prunes computations involving input-output dependencies that are strongly decayed by the forget gate. In particular, our method performs *provably safe* pruning via a dynamically set pruning threshold that guarantees the pruned attention weights are negligible. We apply ACP to language model pretraining with FoX and show it consistently reduces the number of FLOPs and memory accesses in softmax attention by around 70\% across different model sizes and context lengths, resulting in a roughly 50\% to 70\% reduction in attention runtime (or a 2--3

2025-07-06

colmweb.org/COLM/2025/Conference (accepté)

openreview.net

JaxPruner: A concise library for sparsity research

Joo Hyung Lee

Wonpyo Park

Nicole Elyse Mitchell

Jonathan Pilault

Gintare Karolina Dziugaite

Han-Byul Kim

Namhoon Lee

Elias Frantar

Yun Long

Amir Yazdanbakhsh

Shivani Agrawal

Suvinay Subramanian

Xin Wang

Sheng-Chun Kao

Xingyao Zhang

Trevor Gale

Aart J.C. Bik

Woohyun Han

Milen Ferev

Zhonglin Han … (voir 5 de plus)

Hong-Seok Kim

Yann Dauphin

Utku Evci

This paper introduces JaxPruner, an open-source JAX-based pruning and sparse training library for machine learning research. JaxPruner aims … (voir plus)to accelerate research on sparse neural networks by providing concise implementations of popular pruning and sparse training algorithms with minimal memory and latency overhead. Algorithms implemented in JaxPruner use a common API and work seamlessly with the popular optimization library Optax, which, in turn, enables easy integration with existing JAX based libraries. We demonstrate this ease of integration by providing examples in four different codebases: Scenic, t5x, Dopamine and FedJAX and provide baseline experiments on popular benchmarks.

2024-01-07

Conference on Parsimony and Learning (publié)

proceedings.mlr.press

Mixture of Experts in a Mixture of RL settings

Timon Willi

Gintare Karolina Dziugaite

Jakob Nicolaus Foerster

2023-12-31

RLC (publié)

openreview.net

On the consistency of hyper-parameter selection in value-based deep reinforcement learning

João Guilherme Madeira Araújo

Aaron Courville

Deep reinforcement learning (deep RL) has achieved tremendous success on various domains through a combination of algorithmic design and car… (voir plus)eful selection of hyper-parameters. Algorithmic improvements are often the result of iterative enhancements built upon prior approaches, while hyper-parameter choices are typically inherited from previous methods or fine-tuned specifically for the proposed technique. Despite their crucial impact on performance, hyper-parameter choices are frequently overshadowed by algorithmic advancements. This paper conducts an extensive empirical study focusing on the reliability of hyper-parameter selection for value-based deep reinforcement learning agents, including the introduction of a new score to quantify the consistency and reliability of various hyper-parameters. Our findings not only help establish which hyper-parameters are most critical to tune, but also help clarify which tunings remain consistent across different training regimes.

2023-12-31

RLJ (publié)