NeuroGenesysThe research we build on.
1,514 papers by other researchers that our work cites, from continual learning and verification to language models, agents and hardware. Each entry links to the paper on arXiv and to where we use it. 301 are cited on published pages of this site; the rest in the research notes behind our studies. Our own papers are in the archive.
- 2026-10arXiv 2610.03713What Should World Models Forget? Stratified Retention for Continual Adaptation
Nishit Anand, Ramani Duraiswami, Dinesh Manocha · Machine learning
Continual learning treats degradation on previously seen data as evidence of failure, a convention inherited from settings with a stationary prediction target, where a correct label remains correct indefinitely.
Cited inStudy: Genesys program prior art - 2026-09arXiv 2609.22055Benchmarking World Models for Continual Learning on Compositional Tasks
Haoyu Zhou, Joe Watson, Anson Lei et al. · Machine learning
A desirable property of a world model is the ability to learn continually across tasks, adapting to new environments without forgetting what the agent has already learnt.
Cited inStudy: Genesys program prior art - 2026-07arXiv 2607.19749The World Model Remembers, the Actor Forgets: Dream Rehearsal for Continual Model-Based RL
Gurp Nijjer · Machine learning
Model-based reinforcement-learning agents of the DreamerV3 family forget catastrophically when trained on task sequences, even when an unbounded replay buffer preserves every earlier experience.
Cited inStudy: Genesys program prior art - 2026-06arXiv 2606.30317MCP Server Architecture Patterns for LLM-Integrated Applications
Carson Rodrigues, Oysturn Vas · Society, software & economics
The Model Context Protocol (MCP), introduced by Anthropic in November 2024, defines a standardized interface for connecting large language models (LLMs) to external tools, data sources, and services.
- 2026-06arXiv 2606.11435Agent Skill Evaluation and Evolution: Frameworks and Benchmarks
Kexin Ding, Yang Zhou, Can Jin et al. · Language models & NLP
The growth of agent skills has transformed how agentic systems are built, evaluated, and deployed. As skill libraries continue to scale, rigorous evaluation becomes critical to ensuring their utility, quality, and safety in real-world applications.
Cited inStudy: Genesys program prior art - 2026-06arXiv 2606.03979Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
Ali Behrouz, Farnoosh Hashemi, Adel Javanmard et al. · Machine learning
The past few decades have witnessed significant advances in the design of machine learning algorithms, from early studies on task-specific shallow models to more general deep Large Language Models (LLMs).
Cited inInvestors are paying for agents that learn on the job. The hard part is knowing what they forgot.To keep what a model knows, control what it is allowed to moveWhat a model lets into long-term memory matters more than how it learnsStudy: Fortifying knowledge in continual learningStudy: Genesys program prior artStudy: Hardware guardian core for continual learningStudy: LLMs modifying open model weightsStudy: Logical coherence of LLM world modelsStudy: Memory world models and source trustStudy: Seven continual learning methods tested - 2026-05arXiv 2605.26820Can Vision-Language-Action Models Learn from Real-World Data Continually without Forgetting?
Jiarun Zhu, Yijun Hong, Xiaoquan Sun et al. · Robotics & control
Vision-Language-Action (VLA) models provide a promising foundation for general-purpose robotics, yet their real-world deployment demands the ability to continually acquire new skills without forgetting prior ones.
Cited inStudy: Genesys program prior art - 2026-05arXiv 2605.24050More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries
Hongwen Song, Song Wei · Society, software & economics
Skill libraries allow LLM agents to load task-specific instructions on demand, letting non-expert users solve domain-specific tasks through natural language without knowing which skills exist or how they work.
- 2026-05arXiv 2605.05726SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
Ryangkyung Kang, Hongcheol Cho, Youngeun Kim · AI & agents
As LLM agents are increasingly deployed with large libraries of reusable skills, selecting the right skill for a user request has become a critical systems challenge.
- 2026-04arXiv 2604.05333Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
Dawei Liu, Zongxia Li, Hongyang Du et al. · AI & agents
As LLM agents act across personal applications, web browsers, and other interfaces, their reusable skill libraries can scale to thousands of skills. This scale introduces two challenges.
Cited inStudy: Genesys program prior art - 2026-03arXiv 2603.03818Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
Huihan Liu, Changyeon Kim, Bo Liu et al. · Machine learning
Continual learning is a long-standing challenge in robot policy learning, where a policy must acquire new skills over time without catastrophically forgetting previously learned ones.
Cited inStudy: Genesys program prior art - 2026-02arXiv 2602.16653Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environments
Yangjie Xu, Lujun Li, Lama Sleem et al. · AI & agents
Skills are getting increasingly used in recent agentic frameworks, performing robustly with proprietary LLMs. Yet, their effectiveness for small and medium-sized open-source models (270M--80B) remains underexplored, especially under industrial, resource-constrained conditions.
- 2026-02arXiv 2602.05370Mining or Synthesis? Rethinking Exploration Efficiency in Iterative Alignment of Mathematical Reasoning
Jun Rao, Zixiong Yu, Xuebo Liu et al. · Language models & NLP
Iterative Direct Preference Optimization (DPO) has emerged as a widely used paradigm for aligning Large Language Models on reasoning tasks. Existing approaches typically rely on Best-of-N sampling () to mine positive trajectories from the distribution tail.
Cited inStudy: Genesys program prior art - 2026-02arXiv 2602.01270Mixture-of-World Models: Scaling Multi-Task Reinforcement Learning with Modular Latent Dynamics
Boxuan Zhang, Weipu Zhang, Zhaohan Feng et al. · Machine learning
A fundamental challenge in multi-task reinforcement learning (MTRL) is achieving sample efficiency in visual domains where tasks exhibit substantial heterogeneity in both observations and dynamics.
Cited inStudy: Genesys program prior art - 2026-01arXiv 2601.04748When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail
Xiaoxiao Li · AI & agents
Multi-agent AI systems have proven effective for complex reasoning. These systems are compounded by specialized agents, which collaborate through explicit communication, but incur substantial computational overhead.
Cited inStudy: Genesys program prior art - 2025-10arXiv 2510.15103Continual Learning via Sparse Memory Finetuning
Jessy Lin, Luke Zettlemoyer, Gargi Ghosh et al. · Language models & NLP
Modern language models are powerful, but typically static after deployment. A major obstacle to building models that continually learn over time is catastrophic forgetting, where updating on new data erases previously acquired capabilities.
Cited inTo keep what a model knows, control what it is allowed to moveStudy: Fortifying knowledge in continual learningStudy: Genesys program prior artStudy: Hardware guardian core for continual learningStudy: Memory world models and source trustStudy: Seven continual learning methods testedStudy: Weight editing to prevent forgetting - 2025-08arXiv 2508.20453MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
Zhenting Wang, Qi Chang, Hemani Patel et al. · Language models & NLP
We introduce MCP-Bench, a benchmark for evaluating large language models (LLMs) on realistic, multi-step tasks that demand tool use, cross-tool coordination, precise parameter control, and planning/reasoning for solving tasks.
- 2025-08arXiv 2508.14704MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers
Ziyang Luo, Zhiqi Shen, Wenzhuo Yang et al. · AI & agents
The Model Context Protocol has emerged as a transformative standard for connecting large language models to external data sources and tools, rapidly gaining adoption across major AI providers and development platforms.
Cited inStudy: Genesys program prior art - 2025-08arXiv 2508.07575MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmark
Shiqing Fan, Xichen Ding, Liang Zhang et al. · AI & agents
LLMs' capabilities are enhanced by using function calls to integrate various data sources or API results into the context window. Typical tools include search, web crawlers, maps, financial data, file systems, and browser usage, etc.
Cited inStudy: Genesys program prior art - 2025-08arXiv 2508.01780LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?
Guozhao Mo, Wenliang Zhong, Jiawei Chen et al. · AI & agents
Model Context Protocol (MCP) has become a key infrastructure for connecting LLMs with external tools, scaling to 10,000+ MCP servers with diverse tools.
- 2025-07arXiv 2507.12399ROC-n-reroll: How verifier imperfection affects test-time scaling
Florian E. Dorner, Yatong Chen, André F. Cruz et al. · Machine learning
Test-time scaling aims to improve language model performance by leveraging additional compute during inference. Many works have empirically studied techniques such as Best-of-N (BoN) and Rejection Sampling (RS) that make use of a verifier to enable test-time scaling.
Cited inStudy: Genesys program prior art - 2025-07arXiv 2507.09177Continual Reinforcement Learning by Planning with Online World Models
Zichen Liu, Guoji Fu, Chao Du et al. · Machine learning
Continual reinforcement learning (CRL) refers to a naturalistic setting where an agent needs to endlessly evolve, by trial and error, to solve multiple tasks that are presented sequentially.
Cited inStudy: Genesys program prior art - 2025-07arXiv 2507.08794One Token to Fool LLM-as-a-Judge
Yulai Zhao, Haolin Liu, Dian Yu et al. · Machine learning
Large language models (LLMs) are increasingly trusted as automated judges, assisting evaluation and providing reward signals for training other models, particularly in reference-based settings like Reinforcement Learning with Verifiable Rewards (RLVR).
- 2025-06arXiv 2506.21872A Survey of Continual Reinforcement Learning
Chaofan Pan, Xin Yang, Yanhua Li et al. · Machine learning
Reinforcement Learning (RL) is an important machine learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in this field due to the rapid development of deep neural networks.
Cited inStudy: Genesys program prior art - 2025-06arXiv 2506.19248Inference-Time Reward Hacking in Large Language Models
Hadi Khalaf, Claudio Mayrink Verdun, Alex Oesterling et al. · Machine learning
A common paradigm to improve the performance of large language models is optimizing for a reward model. Reward models assign a numerical score to an LLM's output that indicates, for example, how likely it is to align with user preferences or safety goals.
- 2025-06arXiv 2506.18203Shrinking the Generation-Verification Gap with Weak Verifiers
Jon Saad-Falcon, E. Kelly Buchanan, Mayee F. Chen et al. · Language models & NLP
Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates., tools like Lean).
- 2025-06arXiv 2506.09985V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
Mido Assran, Adrien Bardes, David Fan et al. · AI & agents
A major challenge for modern AI is to learn to understand the world and learn to act largely by observation.
- 2025-06arXiv 2506.01937RewardBench 2: Advancing Reward Model Evaluation
Saumya Malik, Valentina Pyatkin, Sander Land et al. · ICLR 2026 · Language models & NLP
Reward models are used throughout the post-training of language models to capture nuanced signals from preference data and provide a training target for optimization across instruction following, reasoning, safety, and more domains.
Cited inStudy: Genesys program prior art - 2025-05arXiv 2505.03275RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation
Tiantian Gan, Qiyao Sun · AI & agents
Large language models (LLMs) struggle to effectively utilize a growing number of external tools, such as those defined by the Model Context Protocol (MCP)\cite{IntroducingMCP}, due to prompt bloat and selection complexity.
- 2025-04arXiv 2504.06188SkillFlow: Scalable and Efficient Agent Skill Retrieval System
Fangzhou Li, Pagkratios Tagkopoulos, Ilias Tagkopoulos · AI & agents
AI agents can extend their capabilities at inference time by loading reusable skills into context, yet equipping an agent with too many skills, particularly irrelevant ones, degrades performance.
Cited inStudy: Genesys program prior art - 2025-03arXiv 2503.21878Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
Audrey Huang, Adam Block, Qinghua Liu et al. · AI & agents
Inference-time computation offers a powerful axis for scaling the performance of language models. However, naively increasing computation in techniques like Best-of-N sampling can lead to performance degradation due to reward hacking.
- 2025-03arXiv 2503.01763Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
Zhengliang Shi, Yuhan Wang, Lingyong Yan et al. · Language models & NLP
Tool learning aims to augment large language models (LLMs) with diverse tools, enabling them to act as agents for solving practical tasks.
- 2025-02arXiv 2502.18581Scalable Best-of-N Selection for Large Language Models via Self-Certainty
Zhewei Kang, Xuandong Zhao, Dawn Song · Language models & NLP
Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models (LLMs) through increased test-time computation. Current state-of-the-art methods often employ computationally intensive reward models for response evaluation and selection.
- 2025-02arXiv 2502.07274Forget Forgetting: Continual Learning in a World of Abundant Memory
Dongkyu Cho, Taesup Moon, Rumi Chunara et al. · Machine learning
Continual learning (CL) has traditionally focused on minimizing exemplar memory, a constraint often misaligned with modern systems where GPU time, not storage, is the primary bottleneck.
- 2025-01arXiv 2501.03575Cosmos World Foundation Model Platform for Physical AI
NVIDIA, :, Niket Agarwal et al. · Vision
Physical AI needs to be trained digitally first. It needs a digital twin of itself, the policy model, and a digital twin of the world, the world model. In this paper, we present the Cosmos World Foundation Model Platform to help developers build customized world models for their Physical AI setups.
- 2024-11arXiv 2411.17501The Limits of Inference Scaling Through Resampling
Benedikt Stroebl, Sayash Kapoor, Arvind Narayanan · Machine learning
Recent research has generated hope that inference scaling, such as resampling solutions until they pass verifiers like unit tests, could allow weaker models to match stronger ones.
- 2024-11arXiv 2411.15399Less is More: Optimizing Function Calling for LLM Execution on Edge Devices
Varatheepan Paramanayakam, Andreas Karatzas, Iraklis Anagnostopoulos et al. · Other
The advanced function-calling capabilities of foundation models open up new possibilities for deploying agents to perform complex API tasks. However, managing large amounts of data and interacting with numerous APIs makes function calling hardware-intensive and costly, especially on edge devices.
Cited inStudy: Genesys program prior art - 2024-10arXiv 2410.11805NesTools: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language Models
Han Han, Tong Zhu, Xiang Zhang et al. · Language models & NLP
Large language models (LLMs) combined with tool learning have gained impressive results in real-world applications. During tool learning, LLMs may call multiple tools in nested orders, where the latter tool call may take the former response as its input parameters.
Cited inStudy: Genesys program prior art - 2024-10arXiv 2410.07137Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates
Xiaosen Zheng, Tianyu Pang, Chao Du et al. · Language models & NLP
0, Arena-Hard-Auto, and MT-Bench, have become popular for evaluating language models due to their cost-effectiveness and scalability compared to human evaluation.
Cited inStudy: Genesys program prior art - 2024-08arXiv 2408.03314Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
Charlie Snell, Jaehoon Lee, Kelvin Xu et al. · Machine learning
Enabling LLMs to improve their outputs by using more test-time computation is a critical step towards building generally self-improving agents that can operate on open-ended natural language.
Built from every arXiv paper cited in our papers, posts, topic hubs, reports and research notes, with titles, authors, dates and abstracts from the arXiv API (updated 2026-11-12). Summaries are the opening sentences of each paper's own abstract, not our assessment; a citation means we used or checked the work, not that we endorse it. Fields follow each paper's primary arXiv category. Papers cited only outside arXiv (journals, proceedings) are not listed yet. Entries are generated from our citations, so a mistyped ID in a note would list the wrong paper; we remove those as we find them. Report a wrong entry.
