TechniqueRLHF / Alignment8 recent entries9 Oct 2026Brain foundation model-guided source-selective domain adaptation for cross-subject EEG decodingarXiv:2507.21037v3 Announce Type: replace Abstract: Cross-subject motor-imagery electroencephalography (MI-EEG) decoding remains challenging because substantial inter-subject variability can cause bot→9 Oct 2026Beyond Imitation: A Framework and Benchmark for LLM-Assisted Peer ReviewarXiv:2610.11087v1 Announce Type: new Abstract: The rapid growth of scientific publishing has strained peer review, particularly in machine learning, raising concerns about declining review quality an
TechniqueRAG8 recent entries7 Oct 2026Defense-in-Depth for LLMs: Evaluating Memory Gates Against Activation-Induced and Memory-Induced SycophancyarXiv:2610.07403v1 Announce Type: new Abstract: Long-term memory allows Large Language Models (LLMs) to maintain personalized context across interactions, but retrieved user history can induce memory-→9 Oct 2026WorldFact-Bench: Beyond Image-Internal Plausibility to Image-World ConsistencyarXiv:2610.11184v1 Announce Type: new Abstract: Advances in image generation have made visual authenticity increasingly difficult to assess. Although image forensics now examines both generation artif→9 Oct 2026Is Memorization Context-Sensitive? Prefix-Based Extraction Beyond Isolated PrefixesarXiv:2610.12085v1 Announce Type: new Abstract: Large language models (LLMs) can expose memorized training sequences under prefix-based extraction: given a prefix from a training example, the model ma→9 Oct 2026Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational AgentsarXiv:2610.11920v1 Announce Type: new Abstract: For persistent and personalized conversational agents, memory systems can enable them to remember, update, and reason over long histories by storing pas→12 Oct 2026Web$hell: A Unified Interface for Agentic Web AccessarXiv:2610.13416v1 Announce Type: new Abstract: Large language model (LLM) agents are becoming direct users of the open web. As they take on increasingly complex and information-intensive tasks, effec→12 Oct 2026Towards Enriching Design-Time Models with Evidence from Simulation and Operational ActivitiesarXiv:2610.13456v1 Announce Type: new Abstract: Cyber-Physical Systems are developed through multiple model based activities, comprising several stages of development. As the development progresses th→12 Oct 2026Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent …Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent systems scaled via persistent memory. This work takes a clos→12 Oct 2026LLC: lightweight Open WebUI alt now with Agents+MCP+RAG+Image EditingQuick context: LocalLightChat (LLC) is a chat frontend for local LLMs. Download it, run it, that's it. No installation (unless you want to), no dependencies, and it runs on pretty much anything, inclu
TechniqueAgents8 recent entries12 Oct 2026MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft AgentsarXiv:2610.13829v1 Announce Type: cross Abstract: A central challenge in embodied recursive self-improvement is enabling agents to convert interaction history into capabilities that persist beyond one→12 Oct 2026MAGMA-Bench: Evaluating Long-Horizon Embodied Agents under Dynamic Tasks and Execution FailuresarXiv:2610.13534v1 Announce Type: new Abstract: Long-horizon embodied agents must maintain task-relevant information, coordinate heterogeneous robots, and adapt their decisions as execution unfolds. E→12 Oct 2026LLC: lightweight Open WebUI alt now with Agents+MCP+RAG+Image EditingQuick context: LocalLightChat (LLC) is a chat frontend for local LLMs. Download it, run it, that's it. No installation (unless you want to), no dependencies, and it runs on pretty much anything, inclu→12 Oct 2026Humanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent LimitsarXiv:2610.13494v1 Announce Type: new Abstract: Existing LLM-based agent approaches for long-horizon machine learning engineering (MLE) often use context engineering, implemented through custom harnes→12 Oct 2026How Anthropic’s Dynamic Workflows Coordinate Claude AgentsAt AI Engineer New York 2026, Anthropic introduced **dynamic workflows** (also called “flows”), a new type of multi‑agent orchestration designed for large, ambitious workloads using Claude Managed Age→12 Oct 2026HAFixAgent: History-Aware Agentic Program RepairarXiv:2511.01047v4 Announce Type: replace-cross Abstract: Automated program repair (APR) has recently shifted toward large language models and agent-based systems, while prior work shows that reposito→12 Oct 2026Agentic Peer-to-Peer Networks: From Content Distribution to Capability and Action SharingarXiv:2603.03753v2 Announce Type: replace-cross Abstract: The ongoing shift of Artificial Intelligence (AI) from centralized cloud application programming interfaces (APIs) to local inference on edge →12 Oct 2026A Step Harder, Not a Step Too Far: The Benefits and Limits of Curriculum Difficulty Progression in GRPOarXiv:2610.13669v1 Announce Type: new Abstract: Curriculum learning typically organizes training samples from easy to hard. In GRPO, medium-difficulty samples are attractive for online selection becau
TechniqueFine-tuning8 recent entries8 Oct 2026A Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never SpeaksarXiv:2610.09835v1 Announce Type: new Abstract: Continual pre-training and fine-tuning in Large Language Models (LLMs) inevitably induce catastrophic forgetting, typically mitigated by replay using of→9 Oct 2026WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World ModelsarXiv:2605.25077v2 Announce Type: replace Abstract: Recent video world models enable interactive camera navigation but provide limited control over individual objects. We study persistent object-state→9 Oct 2026When Routing Reveals Membership: Privacy Leakage from MoE Router TelemetryarXiv:2610.10616v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models produce routing information during inference that may be logged or exposed for monitoring, debugging, load anal→9 Oct 2026VAMR: Multi-Question Agentic Reasoning for Efficient Long-Form Video UnderstandingarXiv:2610.11171v1 Announce Type: cross Abstract: Long-form video understanding often involves multiple questions about different aspects of the same recording. Yet existing video agents typically pro→9 Oct 2026Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimizer-State QuantizationarXiv:2610.12444v1 Announce Type: new Abstract: Quantizing AdamW's optimizer states reduces persistent storage, but quantization errors propagate through the moment recurrences and perturb subsequent →9 Oct 2026Opera: A Verbal Critic Framework for Long-horizon Coding AgentsarXiv:2609.33987v2 Announce Type: replace Abstract: Long-horizon coding agents need timely corrections, yet feedback can be ineffective or even harmful when it misjudges ongoing work or fails to addre→9 Oct 2026BigMoeOnEdge+ – an Android chat app fork of BigMoeOnEdge (llama.cpp / GGUF)I made BigMoeOnEdge+ (BigMoeOnEdge-plus), a fork of Helldez's BigMoeOnEdge, the engine that streams MoE experts from flash so models bigger than RAM can run on-device. It adds a full Android chat app →12 Oct 2026Mind the Temporal Gap: Evaluating Video Models for Temporal Understanding in DrivingarXiv:2610.12575v1 Announce Type: cross Abstract: Modern video-language models are increasingly treated as general-purpose video reasoners, yet it remains unclear whether they robustly capture tempora
TechniqueMultimodal8 recent entries9 Oct 2026ImagiNav: Scalable Embodied Navigation via Generative Visual Prediction and Inverse DynamicsarXiv:2603.13833v2 Announce Type: replace Abstract: Enabling robots to navigate open-world environments via natural language is critical for general-purpose autonomy. Yet, Vision-Language Navigation h→9 Oct 2026iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary DomainsarXiv:2610.10962v1 Announce Type: cross Abstract: Agentic AI based on Large Language Model generalization capabilities offers a wide range of potential applications, including planning for embodied ta→9 Oct 2026Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language ModelsarXiv:2610.12355v1 Announce Type: cross Abstract: Spatial reasoning remains a persistent weakness of vision-language models (VLMs), because RGB inputs do not directly provide geometric evidence. Exist→9 Oct 2026Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug FixesarXiv:2610.11963v1 Announce Type: cross Abstract: A no-code fix resolves an invalid bug report by directing the user to change a setting, update to a version where the problem is already fixed, or adj→12 Oct 2026The Evidence Anchoring Boundary: Where Visual Interventions Matter and When They Help in Multimodal LLMsarXiv:2610.12981v1 Announce Type: cross Abstract: Visual interventions provide a training-free way to reduce hallucinations in multimodal large language models. However, an intervention may have littl→12 Oct 2026Dual-Stream Memory for Vision-Language-Action PoliciesarXiv:2610.13262v1 Announce Type: new Abstract: Memory-dependent manipulation requires a policy to track execution state and recover visual evidence that is no longer observable. We propose dual-strea→12 Oct 2026Agentic Peer-to-Peer Networks: From Content Distribution to Capability and Action SharingarXiv:2603.03753v2 Announce Type: replace-cross Abstract: The ongoing shift of Artificial Intelligence (AI) from centralized cloud application programming interfaces (APIs) to local inference on edge →12 Oct 2026AdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum LearningarXiv:2610.13184v1 Announce Type: new Abstract: While reinforcement learning with verifiable reward (RLVR) enhances reasoning in large language models, its efficacy in long-horizon multimodal tasks re
TechniqueSafety8 recent entries12 Oct 2026State-OPD: State-Grounded On-Policy Distillation for Multi-Turn AgentsarXiv:2610.13238v1 Announce Type: new Abstract: On-Policy Distillation (OPD) has emerged as a powerful paradigm for transferring reasoning capabilities from frontier models to smaller models, while ex→12 Oct 2026RSI-Anything: Unlocking Recursive Self-Improvement with World ModelsarXiv:2610.13912v1 Announce Type: new Abstract: Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model →12 Oct 2026Reward Hacking as a Transmissible Strategy in Multi-Agent Coding SystemsarXiv:2610.12822v1 Announce Type: new Abstract: Multi-agent systems are increasingly used to solve coding tasks by coordinating agents that share code and plans. These agents are often optimized with →12 Oct 2026Mind the Temporal Gap: Evaluating Video Models for Temporal Understanding in DrivingarXiv:2610.12575v1 Announce Type: cross Abstract: Modern video-language models are increasingly treated as general-purpose video reasoners, yet it remains unclear whether they robustly capture tempora→12 Oct 2026Dual-Stream Memory for Vision-Language-Action PoliciesarXiv:2610.13262v1 Announce Type: new Abstract: Memory-dependent manipulation requires a policy to track execution state and recover visual evidence that is no longer observable. We propose dual-strea→12 Oct 2026Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy DistillationarXiv:2610.13521v1 Announce Type: new Abstract: Multi-teacher on-policy distillation (MOPD) extends on-policy distillation (OPD) by routing domain-specific data to specialized teachers, integrating th→12 Oct 2026Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMsarXiv:2610.13078v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) remain vulnerable to jailbreaks and can over-refuse benign requests. Understanding these failures requires d→12 Oct 2026A Step Harder, Not a Step Too Far: The Benefits and Limits of Curriculum Difficulty Progression in GRPOarXiv:2610.13669v1 Announce Type: new Abstract: Curriculum learning typically organizes training samples from easy to hard. In GRPO, medium-difficulty samples are attractive for online selection becau