Retrospective on PAT x ICML 2026 AI Paper Assistant Program
Frege in the Flesh: Biolinguistics and the Neural Enforcement of Syntactic Structures
arXiv:2604.00291v1 Announce Type: new Abstract: Biolinguistics is the interdisciplinary scientific study of the biological foundations, evolution, and genetic basis of human language. It treats language as an innate biological organ or faculty of the mind, rather than a cultural tool,...
Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents
arXiv:2604.00555v1 Announce Type: new Abstract: Enterprise adoption of Large Language Models (LLMs) is constrained by hallucination, domain drift, and the inability to enforce regulatory compliance at the reasoning level. We present a neurosymbolic architecture implemented within the Foundation AgenticOS (FAOS)...
Does Unification Come at a Cost? Uni-SafeBench: A Safety Benchmark for Unified Multimodal Large Models
arXiv:2604.00547v1 Announce Type: new Abstract: Unified Multimodal Large Models (UMLMs) integrate understanding and generation capabilities within a single architecture. While this architectural unification, driven by the deep fusion of multimodal features, enhances model performance, it also introduces important yet underexplored...
How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study
arXiv:2604.00005v1 Announce Type: new Abstract: Emotion plays an important role in human cognition and performance. Motivated by this, we investigate whether analogous emotional signals can shape the behavior of large language models (LLMs) and agents. Existing emotion-aware studies mainly treat...
Large Language Models in the Abuse Detection Pipeline
arXiv:2604.00323v1 Announce Type: new Abstract: Online abuse has grown increasingly complex, spanning toxic language, harassment, manipulation, and fraudulent behavior. Traditional machine-learning approaches dependent on static classifiers and labor-intensive labeling struggle to keep pace with evolving threat patterns and nuanced policy...
Detecting Multi-Agent Collusion Through Multi-Agent Interpretability
arXiv:2604.01151v1 Announce Type: new Abstract: As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human oversight. While linear probes on model activations have shown promise for detecting deception...
Signals: Trajectory Sampling and Triage for Agentic Interactions
arXiv:2604.00356v1 Announce Type: new Abstract: Agentic applications based on large language models increasingly rely on multi-step interaction loops involving planning, action execution, and environment feedback. While such systems are now deployed at scale, improving them post-deployment remains challenging. Agent trajectories...
How Trustworthy Are LLM-as-Judge Ratings for Interpretive Responses? Implications for Qualitative Research Workflows
arXiv:2604.00008v1 Announce Type: cross Abstract: As qualitative researchers show growing interest in using automated tools to support interpretive analysis, a large language model (LLM) is often introduced into an analytic workflow as is, without systematic evaluation of interpretive quality or...
RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning
arXiv:2604.00790v1 Announce Type: new Abstract: While large language models (LLMs) have demonstrated strong performance on complex reasoning tasks such as competitive programming (CP), existing methods predominantly focus on single-attempt settings, overlooking their capacity for iterative refinement. In this paper, we...
CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone Detection
arXiv:2604.00716v1 Announce Type: new Abstract: Transformer language models contain localized reasoning circuits, contiguous layer blocks that improve reasoning when duplicated at inference time. Finding these circuits currently requires brute-force sweeps costing 25 GPU hours per model. We propose CircuitProbe, which...
Google now lets you direct avatars through prompts in its Vids app
Google is adding a way to customize and instruct avatars for video creation in the Vids app.
CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe
arXiv:2604.01489v1 Announce Type: new Abstract: High-performance GPU kernels are critical to modern machine learning systems, yet developing efficient implementations remains a challenging, expert-driven process due to the tight coupling between algorithmic structure, memory hierarchy usage, and hardware-specific optimizations. Recent work...
Polysemanticity or Polysemy? Lexical Identity Confounds Superposition Metrics
arXiv:2604.00443v1 Announce Type: new Abstract: If the same neuron activates for both "lender" and "riverside," standard metrics attribute the overlap to superposition--the neuron must be compressing two unrelated concepts. This work explores how much of the overlap is due a...
Efficient and Principled Scientific Discovery through Bayesian Optimization: A Tutorial
arXiv:2604.01328v1 Announce Type: new Abstract: Traditional scientific discovery relies on an iterative hypothesise-experiment-refine cycle that has driven progress for centuries, but its intuitive, ad-hoc implementation often wastes resources, yields inefficient designs, and misses critical insights. This tutorial presents Bayesian Optimisation...
JetPrism: diagnosing convergence for generative simulation and inverse problems in nuclear physics
arXiv:2604.01313v1 Announce Type: new Abstract: High-fidelity Monte Carlo simulations and complex inverse problems, such as mapping smeared experimental observations to ground-truth states, are computationally intensive yet essential for robust data analysis. Conditional Flow Matching (CFM) offers a mathematically robust approach...
Training In-Context and In-Weights Mixtures Via Contrastive Context Sampling
arXiv:2604.01601v1 Announce Type: new Abstract: We investigate training strategies that co-develop in-context learning (ICL) and in-weights learning (IWL), and the ability to switch between them based on context relevance. Although current LLMs exhibit both modes, standard task-specific fine-tuning often erodes...
When Reward Hacking Rebounds: Understanding and Mitigating It with Representation-Level Signals
arXiv:2604.01476v1 Announce Type: new Abstract: Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task. We systematically study this phenomenon in coding tasks using an environment-manipulation setting, where models...
FourierMoE: Fourier Mixture-of-Experts Adaptation of Large Language Models
arXiv:2604.01762v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) has emerged as a crucial paradigm for adapting large language models (LLMs) under constrained computational budgets. However, standard PEFT methods often struggle in multi-task fine-tuning settings, where diverse optimization objectives induce task...
Malliavin Calculus for Counterfactual Gradient Estimation in Adaptive Inverse Reinforcement Learning
arXiv:2604.01345v1 Announce Type: new Abstract: Inverse reinforcement learning (IRL) recovers the loss function of a forward learner from its observed responses adaptive IRL aims to reconstruct the loss function of a forward learner by passively observing its gradients as it...
Soft MPCritic: Amortized Model Predictive Value Iteration
arXiv:2604.01477v1 Announce Type: new Abstract: Reinforcement learning (RL) and model predictive control (MPC) offer complementary strengths, yet combining them at scale remains computationally challenging. We propose soft MPCritic, an RL-MPC framework that learns in (soft) value space while using sample-based...
Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory
arXiv:2604.01007v2 Announce Type: new Abstract: AI agents increasingly operate over extended time horizons, yet their ability to retain, organize, and recall multimodal experiences remains a critical bottleneck. Building effective lifelong memory requires navigating a vast design space spanning architecture, retrieval...
"Who Am I, and Who Else Is Here?" Behavioral Differentiation Without Role Assignment in Multi-Agent LLM Systems
arXiv:2604.00026v1 Announce Type: new Abstract: When multiple large language models interact in a shared conversation, do they develop differentiated social roles or converge toward uniform behavior? We present a controlled experimental platform that orchestrates simultaneous multi-agent discussions among 7 heterogeneous...
Phonological Fossils: Machine Learning Detection of Non-Mainstream Vocabulary in Sulawesi Basic Lexicon
arXiv:2604.00023v1 Announce Type: new Abstract: Basic vocabulary in many Sulawesi Austronesian languages includes forms resisting reconstruction to any proto-form with phonological patterns inconsistent with inherited roots, but whether this non-conforming vocabulary represents pre-Austronesian substrate or independent innovation has not been...
One Panel Does Not Fit All: Case-Adaptive Multi-Agent Deliberation for Clinical Prediction
arXiv:2604.00085v1 Announce Type: new Abstract: Large language models applied to clinical prediction exhibit case-level heterogeneity: simple cases yield consistent outputs, while complex cases produce divergent predictions under minor prompt changes. Existing single-agent strategies sample from one role-conditioned distribution, and multi-agent...
Benchmark for Assessing Olfactory Perception of Large Language Models
arXiv:2604.00002v1 Announce Type: cross Abstract: Here we introduce the Olfactory Perception (OP) benchmark, designed to assess the capability of large language models (LLMs) to reason about smell. The benchmark contains 1,010 questions across eight task categories spanning odor classification, odor...
The Silicon Mirror: Dynamic Behavioral Gating for Anti-Sycophancy in LLM Agents
arXiv:2604.00478v2 Announce Type: new Abstract: Large Language Models (LLMs) increasingly prioritize user validation over epistemic accuracy - a phenomenon known as sycophancy. We present The Silicon Mirror, an orchestration framework that dynamically detects user persuasion tactics and adjusts AI behavior...
MSA-Thinker: Discrimination-Calibration Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment Analysis
arXiv:2604.00013v1 Announce Type: cross Abstract: Multimodal sentiment analysis aims to understand human emotions by integrating textual, auditory, and visual modalities. Although Multimodal Large Language Models (MLLMs) have achieved state-of-the-art performance via supervised fine-tuning (SFT), their end-to-end "black-box" nature limits interpretability....
Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms
arXiv:2604.00012v1 Announce Type: cross Abstract: Despite the impressive performance of general-purpose large language models (LLMs), they often require fine-tuning or post-training to excel at specific tasks. For instance, large reasoning models (LRMs), such as the DeepSeek-R1 series, demonstrate strong reasoning...
Self-Routing: Parameter-Free Expert Routing from Hidden States
arXiv:2604.00421v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) layers increase model capacity by activating only a small subset of experts per token, and typically rely on a learned router to map hidden states to expert assignments. In this work, we ask...