Papers

Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.

Filtered by domain: Exploration and Sparse RewardsClear

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

9 Jul 2026

AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish within minutes and are evaluated only by their final outcome.

Agents Exploration and Sparse Rewards Reinforcement Learning

1021.1/h

QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining

Wei Li, Jun Han, Shuo Zhang et al. · 6 Feb 2026

Financial markets are noisy and non-stationary, making alpha mining highly sensitive to noise in backtesting results and sudden market regime shifts.

Exploration and Sparse Rewards Language Modeling Reinforcement Learning

1.1k

CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery

Jiacheng Zhu, Zijian Zhou, Ao Qu et al. · 2 Apr 2026

Large language model (LLM)-based evolution is a promising approach for open-ended discovery, where progress requires sustained search and knowledge accumulation.

Exploration and Sparse Rewards Language Modeling Reinforcement Learning

8240.2/h

On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models

Yuexiang Xie, Yaliang Li, Yanxi Chen et al. · 3 Feb 2026

The paper establishes a theoretical framework for analyzing entropy dynamics in reinforcement fine-tuning of large language models, deriving expressions for entropy change and proposing entropy control methods based on discriminant analysis.

Exploration and Sparse Rewards Language Modeling Reinforcement Learning

652

π-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs

Jun Wang, Zheng Zhu, XiaoFeng Wang et al. · 2 Mar 2026

Flow-based vision-language-action (VLA) models excel in embodied control but suffer from intractable likelihoods during multi-step sampling, hindering online reinforcement learning.

Exploration and Sparse Rewards Reinforcement Learning Robotics

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

1 May 2026

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets.

Exploration and Sparse Rewards Language Modeling Reinforcement Learning

700.3/h

AutoMem: Automated Learning of Memory as a Cognitive Skill

1 Jul 2026

Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize knowledge--a capacity known in cognitive science as metamemory. We bring this perspective to LLMs by treating memory management as a trainable skill.

Exploration and Sparse Rewards Language Modeling

1200.2/h

Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?

24 Jun 2026

Multi-fingered robots promise the speed and dexterity of human hands, yet challenging problems such as precise assembly have remained out of reach. These tasks are contact-rich, making data collection for imitation learning difficult, and sparse-reward, making direct exploration…

Exploration and Sparse Rewards Reinforcement Learning

600.2/h

Hallucination in World Models is Predictable and Preventable

25 Jun 2026

Modern generative world models render increasingly realistic action-controllable futures, yet they frequently hallucinate: rollouts remain visually fluent while drifting from the ground-truth dynamics.

Exploration and Sparse Rewards World Models

770.0/h

SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe

3 Jul 2026

While skill optimization for autonomous agents has gained traction, existing methods rely on complex pipelines. This leaves a fundamental question unaddressed: What constitutes a minimal viable pipeline for skill optimization, where every component is justified by theory or…

Agents Coding Agents Exploration and Sparse Rewards Reinforcement Learning

Towards Autonomous and Auditable Medical Imaging Model Development

12 Jul 2026

Large language model (LLM) agents are beginning to automate machine learning engineering (MLE) by coupling planning, code execution, debugging, and empirical feedback. Translating this capability to medical imaging remains difficult because each task imposes modality-specific…

Exploration and Sparse Rewards Language Modeling Medical Imaging Reinforcement Learning