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.
- 2025-09arXiv 2509.15631Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models
Tomoya Yamashita, Akira Ito, Yuuki Yamanaka et al. · Language models & NLP
As large language models (LLMs) are increasingly deployed across various applications, privacy and copyright concerns have heightened the need for more effective LLM unlearning techniques.
- 2025-09arXiv 2509.19372Representation-based Broad Hallucination Detectors Fail to Generalize Out of Distribution
Zuzanna Dubanowska, Maciej Żelaszczyk, Michał Brzozowski et al. · Machine learning
We critically assess the efficacy of the current SOTA in hallucination detection and find that its performance on the RAGTruth dataset is largely driven by a spurious correlation with data.
- 2025-09arXiv 2509.13782Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysis
Yu Ge, Linna Xie, Zhong Li et al. · Society, software & economics
Large Language Model Powered Multi-Agent Systems (MASs) are increasingly employed to automate complex real-world problems, such as programming and scientific discovery.
Cited inInternal notes - 2025-09arXiv 2509.12951Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories
Shilian Chen, Jie Zhou, Tianyu Huai et al. · AI & agents
Model merging refers to the process of integrating multiple distinct models into a unified model that preserves and combines the strengths and capabilities of the individual models.
- 2025-09arXiv 2509.21344Linear probes rely on textual evidence: Results from leakage mitigation studies in language models
Gerard Boxo, Aman Neelappa, Shivam Raval · AI & agents
White-box monitors are a popular technique for detecting potentially harmful behaviours in language models. While they perform well in general, their effectiveness in detecting text-ambiguous behaviour is disputed.
- 2025-09arXiv 2509.11106Fluid Language Model Benchmarking
Valentin Hofmann, David Heineman, Ian Magnusson et al. · Language models & NLP
Language model (LM) benchmarking faces several challenges: comprehensive evaluations are costly, benchmarks often fail to measure the intended capabilities, and evaluation quality can degrade due to labeling errors and benchmark saturation.
- 2025-09arXiv 2509.18137LoRALib: A Standardized Benchmark for Evaluating LoRA-MoE Methods
Shaoheng Wang, Yao Lu, Yuqi Li et al. · Machine learning
As a parameter efficient fine-tuning (PEFT) method, low-rank adaptation (LoRA) can save significant costs in storage and computing, but its strong adaptability to a single task is often accompanied by insufficient cross-task generalization capabilities.
- 2025-09arXiv 2509.10147Virtual Agent Economies
Nenad Tomasev, Matija Franklin, Joel Z. Leibo et al. · AI & agents
The rapid adoption of autonomous AI agents is giving rise to a new economic layer where agents transact and coordinate at scales and speeds beyond direct human oversight.
- 2025-09arXiv 2509.07892Sequential Test for Practical Significance: Truncated Mixture Sequential Probability Ratio Test
Kyu Min Shim · Statistics & theory
We present a sequential testing method to identify a practically significant effect.
Cited inInternal notes - 2025-09arXiv 2509.06608Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors
Viacheslav Sinii, Nikita Balagansky, Gleb Gerasimov et al. · Machine learning
The mechanisms by which reasoning training reshapes LLMs' internal computations remain unclear. We study lightweight steering vectors inserted into the base model's residual stream and trained with a reinforcement-learning objective.
- 2025-09arXiv 2509.06100Orthogonal Low-rank Adaptation in Lie Groups for Continual Learning of Large Language Models
Kefan Cao, Shuaicheng Wu · Language models & NLP
Large language models (LLMs) suffer from catastrophic forgetting in sequential multi-task learning., O-LoRA, N-LoRA) mitigate interference via low-rank subspace orthogonality, but additive updates distort the intrinsic geometry of model parameters.
- 2025-09arXiv 2509.05396Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate
Andrea Wynn, Harsh Satija, Gillian Hadfield · Language models & NLP
While multi-agent debate has been proposed as a promising strategy for improving AI reasoning ability, we find that debate can sometimes be harmful rather than helpful.
- 2025-09arXiv 2509.04259RL's Razor: Why Online Reinforcement Learning Forgets Less
Idan Shenfeld, Jyothish Pari, Pulkit Agrawal · Machine learning
Comparison of fine-tuning models with reinforcement learning (RL) and supervised fine-tuning (SFT) reveals that, despite similar performance at a new task, RL preserves prior knowledge and capabilities significantly better.
- 2025-09arXiv 2509.04664Why Language Models Hallucinate
Adam Tauman Kalai, Ofir Nachum, Santosh S. Vempala et al. · Language models & NLP
Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty.
- 2025-08arXiv 2508.21296MyGO: Memory Yielding Generative Offline-consolidation for Lifelong Learning Systems
Shihao Ji, Zihui Song · Machine learning
Continual or Lifelong Learning aims to develop models capable of acquiring new knowledge from a sequence of tasks without catastrophically forgetting what has been learned before.
- 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 2508.18765Governance-as-a-Service: A Multi-Agent Framework for AI System Compliance and Policy Enforcement
Suyash Gaurav, Jukka Heikkonen, Jatin Chaudhary · Machine learning
As AI systems evolve into distributed ecosystems with autonomous execution, asynchronous reasoning, and multi-agent coordination, the absence of scalable, decoupled governance poses a structural risk.
- 2025-08arXiv 2509.03531Real-Time Detection of Hallucinated Entities in Long-Form Generation
Oscar Obeso, Andy Arditi, Javier Ferrando et al. · Language models & NLP
Large language models are now routinely used in high-stakes applications where hallucinations can cause serious harm, such as medical consultations or legal advice.
- 2025-08arXiv 2508.17536Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
Hyeong Kyu Choi, Xiaojin Zhu, Sharon Li · Language models & NLP
Multi-Agent Debate~(MAD) has emerged as a promising paradigm for improving the performance of large language models through collaborative reasoning. Despite recent advances, the key factors driving MAD's effectiveness remain unclear.
Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStable wrong beliefs evade every self-check: a literature synthesis on model self-knowledge and confident errorsStudy: Logical coherence of LLM world modelsStudy: Model self knowledge and confident errorsStudy: Orchestrated specialists and bridge synthesis - 2025-08arXiv 2508.15253Conflict-Aware Soft Prompting for Retrieval-Augmented Generation
Eunseong Choi, June Park, Hyeri Lee et al. · Language models & NLP
Retrieval-augmented generation (RAG) enhances the capabilities of large language models (LLMs) by incorporating external knowledge into their input prompts.
- 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 2508.15050Don't Think Twice! Over-Reasoning Impairs Confidence Calibration
Romain Lacombe, Kerrie Wu, Eddie Dilworth · AI & agents
Large Language Models deployed as question answering tools require robust calibration to avoid overconfidence., 2023) and expanding it to human and planetary health.
- 2025-08arXiv 2508.16651HiCL: Hippocampal-Inspired Continual Learning
Kushal Kapoor, Wyatt Mackey, Yiannis Aloimonos et al. · Machine learning
We propose HiCL, a novel hippocampal-inspired dual-memory continual learning architecture designed to mitigate catastrophic forgetting by using elements inspired by the hippocampal circuitry.
- 2025-08arXiv 2508.12338Wisdom of the Crowd: Reinforcement Learning from Coevolutionary Collective Feedback
Wenzhen Yuan, Shengji Tang, Weihao Lin et al. · AI & agents
Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), but its reliance on expensive human-labeled data or complex reward models severely limits scalability.
- 2025-08arXiv 2508.12531Rethinking Safety in LLM Fine-tuning: An Optimization Perspective
Minseon Kim, Jin Myung Kwak, Lama Alssum et al. · Machine learning
, refusing to respond to harmful user requests, even when using harmless datasets, thus requiring additional safety measures.
- 2025-08arXiv 2508.15805ALAS: Autonomous Learning Agent for Self-Updating Language Models
Dhruv Atreja · Language models & NLP
Large language models (LLMs) often have a fixed knowledge cutoff, limiting their accuracy on emerging information. We present ALAS (Autonomous Learning Agent System), a modular pipeline that continuously updates an LLM's knowledge with minimal human intervention.
- 2025-08arXiv 2508.09834Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
Weigao Sun, Jiaxi Hu, Yucheng Zhou et al. · Language models & NLP
Large Language Models (LLMs) have delivered impressive results in language understanding, generation, reasoning, and pushes the ability boundary of multimodal models.
- 2025-08arXiv 2508.09974Dynamic Mixture-of-Experts for Incremental Graph Learning
Lecheng Kong, Theodore Vasiloudis, Seongjun Yun et al. · Machine learning
Graph incremental learning is a learning paradigm that aims to adapt trained models to continuously incremented graphs and data over time without the need for retraining on the full dataset.
- 2025-08arXiv 2508.09363Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders
Charles O'Neill, Mudith Jayasekara, Max Kirkby · Machine learning
Sparse autoencoders (SAEs) decompose large language model (LLM) activations into latent features that reveal mechanistic structure. Conventional SAEs train on broad data distributions, forcing a fixed latent budget to capture only high-frequency, generic patterns.
- 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 2508.07738Separation and Collaboration: Two-Level Routing Grouped Mixture-of-Experts for Multi-Domain Continual Learning
Jialu Zhou, Dianxi Shi, Shaowu Yang et al. · Machine learning
Multi-Domain Continual Learning (MDCL) acquires knowledge from sequential tasks with shifting class sets and distribution. Despite the Parameter-Efficient Fine-Tuning (PEFT) methods can adapt for this dual heterogeneity, they still suffer from catastrophic forgetting and forward forgetting.
- 2025-08arXiv 2508.08165Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning
Yan Wang, Da-Wei Zhou, Han-Jia Ye · Vision
Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Existing pre-trained model-based CIL methods often freeze the pre-trained network and adapt to incremental tasks using additional lightweight modules such as adapters.
- 2025-08arXiv 2508.06601Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Kyle O'Brien, Stephen Casper, Quentin Anthony et al. · Machine learning
Open-weight AI systems offer unique benefits, including enhanced transparency, open research, and decentralized access. However, they are vulnerable to tampering attacks which can efficiently elicit harmful behaviors by modifying weights or activations.
- 2025-08arXiv 2508.05004R-Zero: Self-Evolving Reasoning LLM from Zero Data
Chengsong Huang, Wenhao Yu, Xiaoyang Wang et al. · Machine learning
Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences.
- 2025-08arXiv 2508.05078From Isolation to Alignment: Unified LoRA for Efficient Multi-Task Learning
Jinda Liu, Yi Chang, Yuan Wu · Language models & NLP
Parameter-Efficient Fine-Tuning (PEFT) is essential for adapting Large Language Models (LLMs) to multi-task scenarios.
- 2025-08arXiv 2508.04676GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay
Yunan Zhang, Shuoran Jiang, Mengchen Zhao et al. · Language models & NLP
The continual learning capability of large language models (LLMs) is crucial for advancing artificial general intelligence.
- 2025-08arXiv 2508.05687Risk Analysis Techniques for Governed LLM-based Multi-Agent Systems
Alistair Reid, Simon O'Callaghan, Liam Carroll et al. · AI & agents
Organisations are starting to adopt LLM-based AI agents, with their deployments naturally evolving from single agents towards interconnected, multi-agent networks.
- 2025-08arXiv 2508.03153Estimating Worst-Case Frontier Risks of Open-Weight LLMs
Eric Wallace, Olivia Watkins, Miles Wang et al. · Machine learning
In this paper, we study the worst-case frontier risks of releasing gpt-oss. We introduce malicious fine-tuning (MFT), where we attempt to elicit maximum capabilities by fine-tuning gpt-oss to be as capable as possible in two domains: biology and cybersecurity.
- 2025-08arXiv 2508.03682Self-Questioning Language Models
Lili Chen, Mihir Prabhudesai, Katerina Fragkiadaki et al. · Machine learning
Can large language models improve without external data -- by generating their own questions and answers?, algebra word problems) and asking the model to generate its own questions.
- 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.
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.
