Trained Persistent Memory for Frozen Decoder-Only LLMs
arXiv:2603.22329v1 Announce Type: new Abstract: Decoder-only language models are stateless: hidden representations are discarded after every forward pass and nothing persists across sessions. Jeong (2026a) showed that trained memory adapters give a frozen encoder-decoder backbone persistent latent-space memory, building on...
Graph Signal Processing Meets Mamba2: Adaptive Filter Bank via Delta Modulation
arXiv:2603.22333v1 Announce Type: new Abstract: State-space models (SSMs) offer efficient alternatives to attention with linear-time recurrence. Mamba2, a recent SSM-based language model, uses selective input gating and a multi-head structure, enabling parallel computation and strong benchmark performance. However, its multi-head...
Problems with Chinchilla Approach 2: Systematic Biases in IsoFLOP Parabola Fits
arXiv:2603.22339v1 Announce Type: new Abstract: Chinchilla Approach 2 is among the most widely used methods for fitting neural scaling laws. Its parabolic approximation introduces systematic biases in compute-optimal allocation estimates, even on noise-free synthetic data. Applied to published Llama 3...
COMPASS-Hedge: Learning Safely Without Knowing the World
arXiv:2603.22348v1 Announce Type: new Abstract: Online learning algorithms often faces a fundamental trilemma: balancing regret guarantees between adversarial and stochastic settings and providing baseline safety against a fixed comparator. While existing methods excel in one or two of these regimes,...
WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement
arXiv:2603.22352v1 Announce Type: new Abstract: Recent progress in reinforcement learning with verifiable rewards (RLVR) offers a practical path to self-improvement of language models, but existing methods face a key trade-off: endogenous self-play can drift over iterations, while corpus-grounded approaches rely...
FAAR: Format-Aware Adaptive Rounding for NVFP4
arXiv:2603.22370v1 Announce Type: new Abstract: Deploying large language models (LLMs) on edge devices requires extremely low-bit quantization. Ultra-low precision formats such as NVFP4 offer a promising solution for reducing memory footprint and accelerating computation. However, existing quantization methods typically rely...
Rethinking Multimodal Fusion for Time Series: Auxiliary Modalities Need Constrained Fusion
arXiv:2603.22372v1 Announce Type: new Abstract: Recent advances in multimodal learning have motivated the integration of auxiliary modalities such as text or vision into time series (TS) forecasting. However, most existing methods provide limited gains, often improving performance only in specific...
Instruction-Tuned, but Not More Verifiable Instruction-Following: A Cross-Task Diagnosis for LoRA Adapters
arXiv:2603.22379v1 Announce Type: new Abstract: Adapters are often selected and deployed based on nominal labels (e.g., instruction-tuned), which implicitly suggest what capability improves after adaptation. We test whether nominal training objectives reliably align with realized cross-task capability gains by evaluating...
Learning When to Act: Interval-Aware Reinforcement Learning with Predictive Temporal Structure
arXiv:2603.22384v1 Announce Type: new Abstract: Autonomous agents operating in continuous environments must decide not only what to do, but when to act. We introduce a lightweight adaptive temporal control system that learns the optimal interval between cognitive ticks from experience,...
Model Predictive Control with Differentiable World Models for Offline Reinforcement Learning
arXiv:2603.22430v1 Announce Type: new Abstract: Offline Reinforcement Learning (RL) aims to learn optimal policies from fixed offline datasets, without further interactions with the environment. Such methods train an offline policy (or value function), and apply it at inference time without...
SkillRouter: Retrieve-and-Rerank Skill Selection for LLM Agents at Scale
arXiv:2603.22455v1 Announce Type: new Abstract: As LLM agent ecosystems grow, the number of available skills (tools, plugins) has reached tens of thousands, making it infeasible to inject all skills into an agent's context. This creates a need for skill routing...
A Foundation Model for Instruction-Conditioned In-Context Time Series Tasks
arXiv:2603.22586v1 Announce Type: new Abstract: In-context learning (ICL) allows a model to adapt at inference time by conditioning on examples rather than updating parameters. Existing time-series foundation models use implicit positional context, retrieval, or task-specific objectives, but rarely explicit instruction-conditioned...
From 50% to Mastery in 3 Days: A Low-Resource SOP for Localizing Graduate-Level AI Tutors via Shadow-RAG
arXiv:2603.20650v1 Announce Type: new Abstract: Deploying high-fidelity AI tutors in schools is often blocked by the Resource Curse -- the need for expensive cloud GPUs and massive data engineering. In this practitioner report, we present a replicable Standard Operating Procedure...
Fast-Slow Thinking RM: Efficient Integration of Scalar and Generative Reward Models
arXiv:2603.20212v1 Announce Type: new Abstract: Reward models (RMs) are critical for aligning Large Language Models via Reinforcement Learning from Human Feedback (RLHF). While Generative Reward Models (GRMs) achieve superior accuracy through chain-of-thought (CoT) reasoning, they incur substantial computational costs. Conversely,...
Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs
arXiv:2603.20209v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) combine the linguistic strengths of LLMs with the ability to process multimodal data, enbaling them to address a broader range of visual tasks. Because MLLMs aim at more general, human-like...
ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics
arXiv:2603.20260v1 Announce Type: new Abstract: The integration of Large Language Models into Multi-Agent Systems (MAS) has enabled the so-lution of complex, long-horizon tasks through collaborative reasoning. However, this collec-tive intelligence is inherently fragile, as a single logical fallacy can rapidly...
Position: Multi-Agent Algorithmic Care Systems Demand Contestability for Trustworthy AI
arXiv:2603.20595v1 Announce Type: new Abstract: Multi-agent systems (MAS) are increasingly used in healthcare to support complex decision-making through collaboration among specialized agents. Because these systems act as collective decision-makers, they raise challenges for trust, accountability, and human oversight. Existing approaches...
Enhancing Safety of Large Language Models via Embedding Space Separation
arXiv:2603.20206v1 Announce Type: new Abstract: Large language models (LLMs) have achieved impressive capabilities, yet ensuring their safety against harmful prompts remains a critical challenge. Recent work has revealed that the latent representations (embeddings) of harmful and safe queries in LLMs...
NeurIPS Datasets & Benchmarks Track: From Art to Science in AI Evaluations
Domain-Specialized Tree of Thought through Plug-and-Play Predictors
arXiv:2603.20267v1 Announce Type: new Abstract: While Large Language Models (LLMs) have advanced complex reasoning, prominent methods like the Tree of Thoughts (ToT) framework face a critical trade-off between exploration depth and computational efficiency. Existing ToT implementations often rely on heavyweight...
Profit is the Red Team: Stress-Testing Agents in Strategic Economic Interactions
arXiv:2603.20925v1 Announce Type: new Abstract: As agentic systems move into real-world deployments, their decisions increasingly depend on external inputs such as retrieved content, tool outputs, and information provided by other actors. When these inputs can be strategically shaped by adversaries,...
gUFO: A Gentle Foundational Ontology for Semantic Web Knowledge Graphs
arXiv:2603.20948v1 Announce Type: new Abstract: gUFO is a lightweight implementation of the Unified Foundational Ontology (UFO) suitable for Semantic Web OWL 2 DL applications. UFO is a mature foundational ontology with a rich axiomatization and that has been employed in...
Improving Coherence and Persistence in Agentic AI for System Optimization
arXiv:2603.21321v1 Announce Type: new Abstract: Designing high-performance system heuristics is a creative, iterative process requiring experts to form hypotheses and execute multi-step conceptual shifts. While Large Language Models (LLMs) show promise in automating this loop, they struggle with complex system...
The AI Scientific Community: Agentic Virtual Lab Swarms
arXiv:2603.21344v1 Announce Type: new Abstract: In this short note we propose using agentic swarms of virtual labs as a model of an AI Science Community. In this paradigm, each particle in the swarm represents a complete virtual laboratory instance, enabling...
LLM-Driven Heuristic Synthesis for Industrial Process Control: Lessons from Hot Steel Rolling
arXiv:2603.20537v1 Announce Type: new Abstract: Industrial process control demands policies that are interpretable and auditable, requirements that black-box neural policies struggle to meet. We study an LLM-driven heuristic synthesis framework for hot steel rolling, in which a language model iteratively...
A Framework for Low-Latency, LLM-driven Multimodal Interaction on the Pepper Robot
arXiv:2603.21013v1 Announce Type: new Abstract: Despite recent advances in integrating Large Language Models (LLMs) into social robotics, two weaknesses persist. First, existing implementations on platforms like Pepper often rely on cascaded Speech-to-Text (STT)->LLM->Text-to-Speech (TTS) pipelines, resulting in high latency and...
Graph of States: Solving Abductive Tasks with Large Language Models
arXiv:2603.21250v1 Announce Type: new Abstract: Logical reasoning encompasses deduction, induction, and abduction. However, while Large Language Models (LLMs) have effectively mastered the former two, abductive reasoning remains significantly underexplored. Existing frameworks, predominantly designed for static deductive tasks, fail to generalize...
Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systems
arXiv:2603.20578v1 Announce Type: new Abstract: The prevailing approach to improving large language model (LLM) reasoning has centered on expanding context windows, implicitly assuming that more tokens yield better performance. However, empirical evidence - including the "lost in the middle" effect...
LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs
arXiv:2603.20293v1 Announce Type: new Abstract: Text-attributed graphs, where nodes are enriched with textual attributes, have become a powerful tool for modeling real-world networks such as citation, social, and transaction networks. However, existing methods for learning from these graphs often assume...
FinReflectKG -- HalluBench: GraphRAG Hallucination Benchmark for Financial Question Answering Systems
arXiv:2603.20252v1 Announce Type: new Abstract: As organizations increasingly integrate AI-powered question-answering systems into financial information systems for compliance, risk assessment, and decision support, ensuring the factual accuracy of AI-generated outputs becomes a critical engineering challenge. Current Knowledge Graph (KG)-augmented QA...