Post-Routing Arithmetic in Llama-3: Last-Token Result Writing and Rotation-Structured Digit Directions
arXiv:2602.19109v1 Announce Type: new Abstract: We study three-digit addition in Meta-Llama-3-8B (base) under a one-token readout to characterize how arithmetic answers are finalized after cross-token routing becomes causally irrelevant. Causal residual patching and cumulative attention ablations localize a sharp boundary...
K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model
arXiv:2602.19128v1 Announce Type: new Abstract: Optimizing GPU kernels is critical for efficient modern machine learning systems yet remains challenging due to the complex interplay of design factors and rapid hardware evolution. Existing automated approaches typically treat Large Language Models (LLMs)...
DoAtlas-1: A Causal Compilation Paradigm for Clinical AI
arXiv:2602.19158v1 Announce Type: new Abstract: Medical foundation models generate narrative explanations but cannot quantify intervention effects, detect evidence conflicts, or validate literature claims, limiting clinical auditability. We propose causal compilation, a paradigm that transforms medical evidence from narrative text into...
Beyond Behavioural Trade-Offs: Mechanistic Tracing of Pain-Pleasure Decisions in an LLM
arXiv:2602.19159v1 Announce Type: new Abstract: Prior behavioural work suggests that some LLMs alter choices when options are framed as causing pain or pleasure, and that such deviations can scale with stated intensity. To bridge behavioural evidence (what the model does)...
Reasoning Capabilities of Large Language Models. Lessons Learned from General Game Playing
arXiv:2602.19160v1 Announce Type: new Abstract: This paper examines the reasoning capabilities of Large Language Models (LLMs) from a novel perspective, focusing on their ability to operate within formally specified, rule-governed environments. We evaluate four LLMs (Gemini 2.5 Pro and Flash...
Characterizing MARL for Energy Control: A Multi-KPI Benchmark on the CityLearn Environment
arXiv:2602.19223v1 Announce Type: new Abstract: The optimization of urban energy systems is crucial for the advancement of sustainable and resilient smart cities, which are becoming increasingly complex with multiple decision-making units. To address scalability and coordination concerns, Multi-Agent Reinforcement Learning...
Robust Exploration in Directed Controller Synthesis via Reinforcement Learning with Soft Mixture-of-Experts
arXiv:2602.19244v1 Announce Type: new Abstract: On-the-fly Directed Controller Synthesis (OTF-DCS) mitigates state-space explosion by incrementally exploring the system and relies critically on an exploration policy to guide search efficiently. Recent reinforcement learning (RL) approaches learn such policies and achieve promising...
Automated Generation of Microfluidic Netlists using Large Language Models
arXiv:2602.19297v1 Announce Type: new Abstract: Microfluidic devices have emerged as powerful tools in various laboratory applications, but the complexity of their design limits accessibility for many practitioners. While progress has been made in microfluidic design automation (MFDA), a practical and...
ALPACA: A Reinforcement Learning Environment for Medication Repurposing and Treatment Optimization in Alzheimer's Disease
arXiv:2602.19298v1 Announce Type: new Abstract: Evaluating personalized, sequential treatment strategies for Alzheimer's disease (AD) using clinical trials is often impractical due to long disease horizons and substantial inter-patient heterogeneity. To address these constraints, we present the Alzheimer's Learning Platform for...
Time Series, Vision, and Language: Exploring the Limits of Alignment in Contrastive Representation Spaces
arXiv:2602.19367v1 Announce Type: new Abstract: The Platonic Representation Hypothesis posits that learned representations from models trained on different modalities converge to a shared latent structure of the world. However, this hypothesis has largely been examined in vision and language, and...
Artificial Intelligence for Modeling & Simulation in Digital Twins
arXiv:2602.19390v1 Announce Type: new Abstract: The convergence of modeling & simulation (M&S) and artificial intelligence (AI) is leaving its marks on advanced digital technology. Pertinent examples are digital twins (DTs) - high-fidelity, live representations of physical assets, and frequent enablers...
IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking
arXiv:2602.19416v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) enables powerful LLM alignment but can introduce reward hacking - models exploit spurious correlations in proxy rewards without genuine alignment. Compounding this, the objectives internalized during RLHF remain opaque,...
Asymptotic Semantic Collapse in Hierarchical Optimization
arXiv:2602.18450v1 Announce Type: new Abstract: Multi-agent language systems can exhibit a failure mode where a shared dominant context progressively absorbs individual semantics, yielding near-uniform behavior across agents. We study this effect under the name Asymptotic Semantic Collapse in Hierarchical Optimization....
From Trial by Fire To Sleep Like a Baby: A Lexicon of Anxiety Associations for 20k English Multiword Expressions
arXiv:2602.18692v1 Announce Type: new Abstract: Anxiety is the unease about a possible future negative outcome. In recent years, there has been growing interest in understanding how anxiety relates to our health, well-being, body, mind, and behaviour. This includes work on...
Semantic Substrate Theory: An Operator-Theoretic Framework for Geometric Semantic Drift
arXiv:2602.18699v1 Announce Type: new Abstract: Most semantic drift studies report multiple signals e.g., embedding displacement, neighbor changes, distributional divergence, and recursive trajectory instability, without a shared explanatory theory that relates them. This paper proposes a formalization of these signals in...
ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Models
arXiv:2602.18721v1 Announce Type: new Abstract: Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, we propose ReHear, a framework for iterative...
DeepInnovator: Triggering the Innovative Capabilities of LLMs
arXiv:2602.18920v1 Announce Type: new Abstract: The application of Large Language Models (LLMs) in accelerating scientific discovery has garnered increasing attention, with a key focus on constructing research agents endowed with innovative capability, i.e., the ability to autonomously generate novel and...
Why Agent Caching Fails and How to Fix It: Structured Intent Canonicalization with Few-Shot Learning
arXiv:2602.18922v1 Announce Type: new Abstract: Personal AI agents incur substantial cost via repeated LLM calls. We show existing caching methods fail: GPTCache achieves 37.9% accuracy on real benchmarks; APC achieves 0-12%. The root cause is optimizing for the wrong property...
Yor-Sarc: A gold-standard dataset for sarcasm detection in a low-resource African language
arXiv:2602.18964v1 Announce Type: new Abstract: Sarcasm detection poses a fundamental challenge in computational semantics, requiring models to resolve disparities between literal and intended meaning. The challenge is amplified in low-resource languages where annotated datasets are scarce or nonexistent. We present...
Capable but Unreliable: Canonical Path Deviation as a Causal Mechanism of Agent Failure in Long-Horizon Tasks
arXiv:2602.19008v1 Announce Type: new Abstract: Why do language agents fail on tasks they are capable of solving? We argue that many such failures are reliability failures caused by stochastic drift from a task's latent solution structure, not capability failures. Every...
Causal Identification from Counterfactual Data: Completeness and Bounding Results
arXiv:2602.23541v1 Announce Type: new Abstract: Previous work establishing completeness results for $\textit{counterfactual identification}$ has been circumscribed to the setting where the input data belongs to observational or interventional distributions (Layers 1 and 2 of Pearl's Causal Hierarchy), since it was...
Planning under Distribution Shifts with Causal POMDPs
arXiv:2602.23545v1 Announce Type: new Abstract: In the real world, planning is often challenged by distribution shifts. As such, a model of the environment obtained under one set of conditions may no longer remain valid as the distribution of states or...
Construct, Merge, Solve & Adapt with Reinforcement Learning for the min-max Multiple Traveling Salesman Problem
arXiv:2602.23579v1 Announce Type: new Abstract: The Multiple Traveling Salesman Problem (mTSP) extends the Traveling Salesman Problem to m tours that start and end at a common depot and jointly visit all customers exactly once. In the min-max variant, the objective...
SleepLM: Natural-Language Intelligence for Human Sleep
arXiv:2602.23605v1 Announce Type: new Abstract: We present SleepLM, a family of sleep-language foundation models that enable human sleep alignment, interpretation, and interaction with natural language. Despite the critical role of sleep, learning-based sleep analysis systems operate in closed label spaces...
AI Must Embrace Specialization via Superhuman Adaptable Intelligence
arXiv:2602.23643v1 Announce Type: new Abstract: Everyone from AI executives and researchers to doomsayers, politicians, and activists is talking about Artificial General Intelligence (AGI). Yet, they often don't seem to agree on its exact definition. One common definition of AGI is...
From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems
arXiv:2602.23701v1 Announce Type: new Abstract: LLM-powered Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex domains but suffer from inherent fragility and opaque failure mechanisms. Existing failure attribution methods, whether relying on direct prompting, costly replays, or supervised fine-tuning, typically...
ProductResearch: Training E-Commerce Deep Research Agents via Multi-Agent Synthetic Trajectory Distillation
arXiv:2602.23716v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents show promise for e-commerce conversational shopping, yet existing implementations lack the interaction depth and contextual breadth required for complex product research. Meanwhile, the Deep Research paradigm, despite advancing information synthesis...
The Auton Agentic AI Framework
arXiv:2602.23720v1 Announce Type: new Abstract: The field of Artificial Intelligence is undergoing a transition from Generative AI -- probabilistic generation of text and images -- to Agentic AI, in which autonomous systems execute actions within external environments on behalf of...
Reasoning-Driven Multimodal LLM for Domain Generalization
arXiv:2602.23777v1 Announce Type: new Abstract: This paper addresses the domain generalization (DG) problem in deep learning. While most DG methods focus on enforcing visual feature invariance, we leverage the reasoning capability of multimodal large language models (MLLMs) and explore the...
EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models
arXiv:2602.23802v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual reasoning and understanding tasks but still struggle to capture the complexity and subjectivity of human emotions. Existing approaches based on supervised fine-tuning often suffer...