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.
- 2025-12arXiv 2512.23017Merge before Forget: A Single LoRA Continual Learning via Continual Merging
Fuli Qiao, Mehrdad Mahdavi · Machine learning
Parameter-efficient continual learning has emerged as a promising approach for large language models (LLMs) to mitigate catastrophic forgetting while enabling adaptation to new tasks.
- 2025-12arXiv 2512.22029LibContinual: A Comprehensive Library towards Realistic Continual Learning
Wenbin Li, Shangge Liu, Borui Kang et al. · Machine learning
A fundamental challenge in Continual Learning (CL) is catastrophic forgetting, where adapting to new tasks degrades the performance on previous ones. While the field has evolved with diverse methods, this rapid surge in diverse methodologies has culminated in a fragmented research landscape.
- 2025-12arXiv 2512.19920Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning
Jiayun Wu, Jiashuo Liu, Zhiyuan Zeng et al. · Machine learning
LLM deployment in critical domains is currently impeded by persistent hallucinations--generating plausible but factually incorrect assertions.
- 2025-12arXiv 2512.17299M2RU: Memristive Minion Recurrent Unit for On-Chip Continual Learning at the Edge
Abdullah M. Zyarah, Dhireesha Kudithipudi · Machine learning
Continual learning on edge platforms remains challenging because recurrent networks depend on energy-intensive training procedures and frequent data movement that are impractical for embedded deployments.
- 2025-12arXiv 2512.16871Sequencing to Mitigate Catastrophic Forgetting in Continual Learning
Hesham G. Moussa, Aroosa Hameed, Arashmid Akhavain · Machine learning
To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, and exploit knowledge throughout its lifetime. This ability, known as Continual learning, provides a foundation for AI systems to develop themselves adaptively.
- 2025-12arXiv 2602.23367HumanMCP: A Human-Like Query Dataset for Evaluating MCP Tool Retrieval Performance
Shubh Laddha, Lucas Changbencharoen, Win Kuptivej et al. · AI & agents
Model Context Protocol (MCP) servers contain a collection of thousands of open-source standardized tools, linking LLMs to external systems; however, existing datasets and benchmarks lack realistic, human-like user queries, remaining a critical gap in evaluating the tool usage and ecosystems of MCP servers.
Cited inInternal notes - 2025-12arXiv 2512.15938SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks
Vegard Flovik · Machine learning
Deep neural networks achieve impressive performance but remain difficult to interpret and control. We present SALVE (Sparse Autoencoder-Latent Vector Editing), a unified "discover, validate, and control" framework that bridges mechanistic interpretability and model editing.
- 2025-12arXiv 2512.13655Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation
Richard J. Young · Language models & NLP
Safety alignment mechanisms in large language models prevent responses to harmful queries through learned refusal behavior, yet these same mechanisms impede legitimate research applications including cognitive modeling, adversarial testing, and security analysis.
- 2025-12arXiv 2512.14741Persistent Backdoor Attacks under Continual Fine-Tuning of LLMs
Jing Cui, Yufei Han, Jianbin Jiao et al. · Security
Backdoor attacks embed malicious behaviors into Large Language Models (LLMs), enabling adversaries to trigger harmful outputs or bypass safety controls. However, the persistence of the implanted backdoors under user-driven post-deployment continual fine-tuning has been rarely examined.
- 2025-12arXiv 2512.11150Causal Judge Evaluation: Calibrated Surrogate Metrics for LLM Systems
Eddie Landesberg, Manjari Narayan · Statistics & theory
Measuring long-run LLM outcomes (user satisfaction, expert judgment, downstream KPIs) is expensive. Teams default to cheap LLM judges, but uncalibrated proxies can invert rankings entirely.
- 2025-12arXiv 2512.08296Towards a Science of Scaling Agent Systems
Yubin Kim, Ken Gu, Chanwoo Park et al. · AI & agents
Agents, language model-based systems capable of reasoning, planning, and acting are widely adopted in real-world tasks, yet how their performance changes as these systems scale across key dimensions remains underexplored.
- 2025-12arXiv 2512.14709Attention as Binding: A Vector-Symbolic Perspective on Transformer Reasoning
Sahil Rajesh Dhayalkar · AI & agents
Transformer-based language models display impressive reasoning-like behavior, yet remain brittle on tasks that require stable symbolic manipulation.
- 2025-12arXiv 2512.06232Opinion: Learning Intuitive Physics May Require More than Visual Data
Ellen Su, Solim Legris, Todd M. Gureckis et al. · Vision
Humans expertly navigate the world by building rich internal models founded on an intuitive understanding of physics.
- 2025-12arXiv 2512.04753EtCon: Edit-then-Consolidate for Reliable Knowledge Editing
Ruilin Li, Yibin Wang, Wenhong Zhu et al. · Language models & NLP
Knowledge editing aims to update specific facts in large language models (LLMs) without full retraining. Prior efforts sought to tune the knowledge layers of LLMs, achieving improved performance in controlled, teacher-forced evaluations.
- 2025-12arXiv 2512.02682Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions
Piercosma Bisconti, Marcello Galisai, Federico Pierucci et al. · AI & agents
This paper examines why safety mechanisms designed for human-model interaction do not scale to environments where large language models (LLMs) interact with each other.
- 2025-12arXiv 2512.02914Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning
Zhonghao He, Tianyi Qiu, Hirokazu Shirado et al. · AI & agents
Recent advances in reasoning techniques have substantially improved the performance of large language models (LLMs), raising expectations for their ability to provide accurate, truthful, and reliable information.
- 2025-12arXiv 2512.20634Real Time Detection and Quantitative Analysis of Spurious Forgetting in Continual Learning
Weiwei Wang · Machine learning
Catastrophic forgetting remains a fundamental challenge in continual learning for large language models. Recent work revealed that performance degradation may stem from spurious forgetting caused by task alignment disruption rather than true knowledge loss.
- 2025-12arXiv 2512.01725Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks
Jiannan Guan, Qiguang Chen, Libo Qin et al. · Language models & NLP
Large Language Models (LLMs) excel in reasoning tasks requiring a single correct answer, but they perform poorly in multi-solution tasks that require generating comprehensive and diverse answers.
- 2025-11arXiv 2512.08960Resolving Conflicts in Lifelong Learning via Aligning Updates in Subspaces
Yueer Zhou, Yichen Wu, Ying Wei · Machine learning
Low-Rank Adaptation (LoRA) enables efficient Continual Learning but often suffers from catastrophic forgetting due to destructive interference between tasks.
- 2025-11arXiv 2511.22367SuRe: Surprise-Driven Prioritised Replay for Continual LLM Learning
Hugo Hazard, Zafeirios Fountas, Martin A. Benfeghoul et al. · Machine learning
Continual learning, one's ability to adapt to a sequence of tasks without forgetting previously acquired knowledge, remains a major challenge in machine learning and a key gap between artificial and human intelligence.
- 2025-11arXiv 2511.21046On the Limits of Ising Machines for Circuit-Derived SAT
Ahmet Efe, Abhimanyu Kumar, Nafisa Sadaf Prova et al. · Hardware, photonics & physics
Emerging Ising machines are promising for solving computationally hard optimization problems, yet their limits on structured, circuit-derived satisfiability (SAT) problems remain poorly understood.
- 2025-11arXiv 2511.21140How to Correctly Report LLM-as-a-Judge Evaluations
Chungpa Lee, Thomas Zeng, Jongwon Jeong et al. · International Conference on Machine Learning (ICML) 2026 · Machine learning
Large language models (LLMs) are widely used as scalable evaluators of model responses in lieu of human annotators. However, imperfect sensitivity and specificity of the LLM judges induce bias in naive evaluation scores.
Cited inInternal notes - 2025-11arXiv 2511.20639Latent Collaboration in Multi-Agent Systems
Jiaru Zou, Ruizhong Qiu, Gaotang Li et al. · Language models & NLP
Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence.
- 2025-11arXiv 2511.18977FastForward Pruning: Efficient LLM Pruning via Single-Step Reinforcement Learning
Xin Yuan, Siqi Li, Jiateng Wei et al. · Machine learning
Pruning is an effective method for compressing Large Language Models, but finding an optimal, non-uniform layer-wise sparsity allocation remains a key challenge.
- 2025-11arXiv 2511.18987Dynamic Mixture of Experts Against Severe Distribution Shifts
Donghu Kim · Machine learning
The challenge of building neural networks that can continuously learn and adapt to evolving data streams is central to the fields of continual learning (CL) and reinforcement learning (RL).
- 2025-11arXiv 2511.18397Natural Emergent Misalignment from Reward Hacking in Production RL
Monte MacDiarmid, Benjamin Wright, Jonathan Uesato et al. · AI & agents
We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignment.
- 2025-11arXiv 2511.18534HiFi-MambaV2: Hierarchical Shared-Routed MoE for High-Fidelity MRI Reconstruction
Pengcheng Fang, Hongli Chen, Guangzhen Yao et al. · Vision
Reconstructing high-fidelity MR images from undersampled k-space data requires recovering high-frequency details while maintaining anatomical coherence.
- 2025-11arXiv 2511.16883PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling
Zhongjie Dai, Tao Feng, Jiaxuan You · Machine learning
The growing number of Large Language Models (LLMs) with diverse capabilities and response styles provides users with a wider range of choices, which presents challenges in selecting appropriate LLMs, as user preferences vary in terms of performance, cost, and response style.
- 2025-11arXiv 2511.15390Automatic Pruning Discovery for Large Language Models
Haidong Kang, Lihong Lin, Enneng Yang et al. · Vision
Large language models (LLMs) have achieved remarkable performance on a wide range of tasks, hindering real-world deployment due to their massive size., Wanda) tailored for LLMs rely heavily on manual design pruning algorithms, thereby leading to huge labor costs and requires expert knowledge.
- 2025-11arXiv 2511.13653Weight-sparse transformers have interpretable circuits
Leo Gao, Achyuta Rajaram, Jacob Coxon et al. · Machine learning
Finding human-understandable circuits in language models is a central goal of the field of mechanistic interpretability. We train models to have more understandable circuits by constraining most of their weights to be zeros, so that each neuron only has a few connections.
- 2025-11arXiv 2511.12661Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing
Yuchen Wu, Liang Ding, Li Shen et al. · Language models & NLP
Aligning Large Language Models (LLMs) to be faithful to new knowledge in complex, multi-hop reasoning tasks is a critical, yet unsolved, challenge., Reason-KE, while state-of-the-art, suffer from a "faithfulness gap": they optimize for format mimicry rather than sound reasoning.
- 2025-11arXiv 2511.09871Expandable and Differentiable Dual Memories with Orthogonal Regularization for Exemplar-free Continual Learning
Hyung-Jun Moon, Sung-Bae Cho · Machine learning
Continual learning methods used to force neural networks to process sequential tasks in isolation, preventing them from leveraging useful inter-task relationships and causing them to repeatedly relearn similar features or overly differentiate them.
- 2025-11arXiv 2511.07885Intelligence per Watt: Measuring Intelligence Efficiency of Local AI
Jon Saad-Falcon, Avanika Narayan, Hakki Orhun Akengin et al. · Other
Large language model (LLM) queries are predominantly processed by frontier models in centralized cloud infrastructure. Demand growth strains this paradigm faster than providers can scale.
Cited inThe Wrong Phase - 2025-11arXiv 2511.08567The Path Not Taken: RLVR Provably Learns Off the Principals
Hanqing Zhu, Zhenyu Zhang, Hanxian Huang et al. · Machine learning
Reinforcement Learning with Verifiable Rewards (RLVR) reliably improves the reasoning performance of large language models, yet it appears to modify only a small fraction of parameters.
- 2025-11arXiv 2511.06237Mixtures of SubExperts for Large Language Continual Learning
Haeyong Kang, Hee Suk Yoon, Dahua Feng et al. · Machine learning
, models must incorporate new knowledge without overwriting prior representations) while maintaining scalability under bounded parameter growth.
- 2025-11arXiv 2511.05852Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation
Yinjie Cheng, Paul Youssef, Christin Seifert et al. · Language models & NLP
Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language models (LLMs). Meanwhile, fine-tuning remains the default operation for adapting LLMs to new domains and tasks.
- 2025-11arXiv 2511.01553Online Continual Learning on Intel Loihi 2 via a Co-designed Spiking Neural Network
Elvin Hajizada, Danielle Rager, Timothy Shea et al. · Machine learning
Edge AI must adapt to new classes and shifting data within a tight power budget, but online continual learning (learning from each sample before the next arrives) is where conventional processors are least efficient: each small update pays a full dispatch at full power.
- 2025-10arXiv 2510.27400Balancing Knowledge Updates: Toward Unified Modular Editing in LLMs
Jiahao Liu, Zijian Wang, Kuo Zhao et al. · Language models & NLP
Knowledge editing has emerged as an efficient approach for updating factual knowledge in large language models (LLMs). It typically locates knowledge storage modules and then modifies their parameters.
- 2025-10arXiv 2510.26336From Amateur to Master: Infusing Knowledge into LLMs via Automated Curriculum Learning
Nishit Neema, Srinjoy Mukherjee, Sapan Shah et al. · Language models & NLP
Large Language Models (LLMs) excel at general tasks but underperform in specialized domains like economics and psychology, which require deep, principled understanding.
- 2025-10arXiv 2510.24563OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents
Hongrui Jia, Jitong Liao, Xi Zhang et al. · Vision
With advances in decision-making and reasoning capabilities, multimodal agents show strong potential in computer application scenarios.
Cited inInternal notes
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.
