6 citations · 6 across the 13 of their papers we have counts for
18 papers
KV-streams for Efficient Compaction in Agentic Reinforcement Learning
Emiliano Penaloza, Dane Malenfant, Dheeraj Vattikonda +15
Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU memory. Context compaction has been the most popular mechanism to alleviate…
Shockingly Simple Self-retrospection Improves Agentic Models Without RL
Jonathan Light, Christopher Zhang Cui, Jeonghye Kim +7
People learn not only by repeating successful actions, but also by recounting and explaining their experiences, revising their understanding to guide future behavior. Can a languag…
GlyphBench: A Playground for Language-Model Reinforcement Learning
Roger Creus Castanyer, Marc-Alexandre Côté, Matthew James Sargent +3
We introduce GlyphBench, an environment suite for reinforcement learning (RL) post-training of language-model agents, with over 360 tasks spanning diverse games. GlyphBench renders…
FrogNano: Training a 4B Coding Agent via Online Task Synthesis
Minseon Kim, Zhengyan Shi, Emiliano Penaloza +14
We present FrogNano, a 4B coding agent designed to tackle software engineering (SWE) tasks efficiently and effectively, even under resource-constrained environments. It is post-tra…
Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier
Lorenz Wolf, Connor Watts, Roger Creus Castanyer +4
The limiting resource for training agents via reinforcement learning (RL) is increasingly frontier task supply: valid, solvable tasks just difficult enough to train the current mod…
unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning
Geoffrey Bradway, Roger Creus Castanyer, Lorenz Wolf +3
Unix competence is the ability to use shell and operating-system primitives as first-class tools, not merely to write programs through a terminal. Current terminal benchmarks tend…
PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play
Roger Creus Castanyer, Geoffrey Bradway, Lorenz Wolf +3
We introduce PopuLoRA, a population-based asymmetric self-play framework for reinforcement learning with verifiable rewards (RLVR) post-training of LLMs. Teachers and students are…
Agentick: A Unified Benchmark for General Sequential Decision-Making Agents
Roger Creus Castanyer, Pablo Samuel Castro, Glen Berseth
AI agent research spans a wide spectrum: from RL agents that learn from scratch to foundation model agents that leverage pre-trained knowledge, yet no unified benchmark enables fai…
Align and Filter: Improving Performance in Asynchronous On-Policy RL
Homayoun Honari, Roger Creus Castanyer, Michael Przystupa +3
Distributed training and increasing the gradient update frequency are practical strategies to accelerate learning and improve performance, but both exacerbate a central challenge:…
ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning
Roger Creus Castanyer, Faisal Mohamed, Pablo Samuel Castro +2
Reinforcement learning (RL) algorithms are highly sensitive to reward function specification, which remains a central challenge limiting their broad applicability. We present ARM-F…
BuilderBench: The Building Blocks of Intelligent Agents
Raj Ghugare, Roger Creus Castanyer, Catherine Ji +4
Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel…
Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning
Roger Creus Castanyer, Johan Obando-Ceron, Lu Li +4
Scaling deep reinforcement learning networks is challenging and often results in degraded performance, yet the root causes of this failure mode remain poorly understood. Several re…
RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning
Mingqi Yuan, Roger Creus Castanyer, Bo Li +3
Extrinsic rewards can effectively guide reinforcement learning (RL) agents in specific tasks. However, extrinsic rewards frequently fall short in complex environments due to the si…
Surprise-Adaptive Intrinsic Motivation for Unsupervised Reinforcement Learning
Adriana Hugessen, Roger Creus Castanyer, Faisal Mohamed +1
Both entropy-minimizing and entropy-maximizing (curiosity) objectives for unsupervised reinforcement learning (RL) have been shown to be effective in different environments, depend…
Improving Intrinsic Exploration by Creating Stationary Objectives
Roger Creus Castanyer, Joshua Romoff, Glen Berseth
Exploration bonuses in reinforcement learning guide long-horizon exploration by defining custom intrinsic objectives. Several exploration objectives like count-based bonuses, pseud…
Centralized control for multi-agent RL in a complex Real-Time-Strategy game
Roger Creus Castanyer
Multi-agent Reinforcement learning (MARL) studies the behaviour of multiple learning agents that coexist in a shared environment. MARL is more challenging than single-agent RL beca…
Which Design Decisions in AI-enabled Mobile Applications Contribute to Greener AI?
Roger Creus Castanyer, Silverio Martínez-Fernández, Xavier Franch
Background: The construction, evolution and usage of complex artificial intelligence (AI) models demand expensive computational resources. While currently available high-performanc…
Integration of Convolutional Neural Networks in Mobile Applications
Roger Creus Castanyer, Silverio Martínez-Fernández, Xavier Franch
When building Deep Learning (DL) models, data scientists and software engineers manage the trade-off between their accuracy, or any other suitable success criteria, and their compl…