FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning
arXiv:2604.03893v1 Announce Type: new Abstract: Breakthroughs in frontier theory often depend on the combination of concrete diagrammatic notations with rigorous logic. While multimodal large language models (MLLMs) show promise in general scientific tasks, current benchmarks often focus on local information...
Diagonal-Tiled Mixed-Precision Attention for Efficient Low-Bit MXFP Inference
arXiv:2604.03950v1 Announce Type: new Abstract: Transformer-based large language models (LLMs) have demonstrated remarkable performance across a wide range of real-world tasks, but their inference cost remains prohibitively high due to the quadratic complexity of attention and the memory bandwidth limitations...
RUQuant: Towards Refining Uniform Quantization for Large Language Models
arXiv:2604.04013v1 Announce Type: new Abstract: The increasing size and complexity of large language models (LLMs) have raised significant challenges in deployment efficiency, particularly under resource constraints. Post-training quantization (PTQ) has emerged as a practical solution by compressing models without requiring...
Single-agent vs. Multi-agents for Automated Video Analysis of On-Screen Collaborative Learning Behaviors
arXiv:2604.03631v1 Announce Type: new Abstract: On-screen learning behavior provides valuable insights into how students seek, use, and create information during learning. Analyzing on-screen behavioral engagement is essential for capturing students' cognitive and collaborative processes. The recent development of Vision Language...
Selective Forgetting for Large Reasoning Models
arXiv:2604.03571v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) generate structured chains of thought (CoTs) before producing final answers, making them especially vulnerable to knowledge leakage through intermediate reasoning steps. Yet, the memorization of sensitive information in the training data...
Cultural Authenticity: Comparing LLM Cultural Representations to Native Human Expectations
arXiv:2604.03493v1 Announce Type: new Abstract: Cultural representation in Large Language Model (LLM) outputs has primarily been evaluated through the proxies of cultural diversity and factual accuracy. However, a crucial gap remains in assessing cultural alignment: the degree to which generated...
When Do Hallucinations Arise? A Graph Perspective on the Evolution of Path Reuse and Path Compression
arXiv:2604.03557v1 Announce Type: new Abstract: Reasoning hallucinations in large language models (LLMs) often appear as fluent yet unsupported conclusions that violate either the given context or underlying factual knowledge. Although such failures are widely observed, the mechanisms by which decoder-only...
Automated Analysis of Global AI Safety Initiatives: A Taxonomy-Driven LLM Approach
arXiv:2604.03533v1 Announce Type: new Abstract: We present an automated crosswalk framework that compares an AI safety policy document pair under a shared taxonomy of activities. Using the activity categories defined in Activity Map on AI Safety as fixed aspects, the...
Beyond Retrieval: Modeling Confidence Decay and Deterministic Agentic Platforms in Generative Engine Optimization
arXiv:2604.03656v1 Announce Type: new Abstract: Generative Engine Optimization (GEO) is rapidly reshaping digital marketing paradigms in the era of Large Language Models (LLMs). However, current GEO strategies predominantly rely on Retrieval-Augmented Generation (RAG), which inherently suffers from probabilistic hallucinations and...
Comparative reversal learning reveals rigid adaptation in LLMs under non-stationary uncertainty
arXiv:2604.04182v1 Announce Type: new Abstract: Non-stationary environments require agents to revise previously learned action values when contingencies change. We treat large language models (LLMs) as sequential decision policies in a two-option probabilistic reversal-learning task with three latent states and switch...
Structural Rigidity and the 57-Token Predictive Window: A Physical Framework for Inference-Layer Governability in Large Language Models
arXiv:2604.03524v1 Announce Type: new Abstract: Current AI safety relies on behavioral monitoring and post-training alignment, yet empirical measurement shows these approaches produce no detectable pre-commitment signal in a majority of instruction-tuned models tested. We present an energy-based governance framework connecting...
PRAISE: Prefix-Based Rollout Reuse in Agentic Search Training
arXiv:2604.03675v1 Announce Type: new Abstract: In agentic search, large language models (LLMs) are trained to perform multi-turn retrieval and reasoning for complex tasks such as multi-hop question answering (QA). However, current search-based Reinforcement Learning (RL) methods suffer from two core...
Unmasking Hallucinations: A Causal Graph-Attention Perspective on Factual Reliability in Large Language Models
arXiv:2604.04020v1 Announce Type: new Abstract: This paper primarily focuses on the hallucinations caused due to AI language models(LLMs).LLMs have shown extraordinary Language understanding and generation capabilities .Still it has major a disadvantage hallucinations which give outputs which are factually incorrect...
NativeTernary: A Self-Delimiting Binary Encoding with Unary Run-Length Hierarchy Markers for Ternary Neural Network Weights, Structured Data, and General Computing Infrastructure
arXiv:2604.03336v1 Announce Type: new Abstract: BitNet b1.58 (Ma et al., 2024) demonstrates that large language models can operate entirely on ternary weights {-1, 0, +1}, yet no native binary wire format exists for such models. NativeTernary closes this gap. We...
Explainable Model Routing for Agentic Workflows
arXiv:2604.03527v1 Announce Type: new Abstract: Modern agentic workflows decompose complex tasks into specialized subtasks and route them to diverse models to minimize cost without sacrificing quality. However, current routing architectures focus exclusively on performance optimization, leaving underlying trade-offs between model...
LightThinker++: From Reasoning Compression to Memory Management
arXiv:2604.03679v1 Announce Type: new Abstract: Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognitive overhead of long thought traces. In this paper, we propose LightThinker, a method that enables LLMs to dynamically...
Neural Global Optimization via Iterative Refinement from Noisy Samples
arXiv:2604.03614v1 Announce Type: new Abstract: Global optimization of black-box functions from noisy samples is a fundamental challenge in machine learning and scientific computing. Traditional methods such as Bayesian Optimization often converge to local minima on multi-modal functions, while gradient-free methods...
Are Arabic Benchmarks Reliable? QIMMA's Quality-First Approach to LLM Evaluation
arXiv:2604.03395v1 Announce Type: new Abstract: We present QIMMA, a quality-assured Arabic LLM leaderboard that places systematic benchmark validation at its core. Rather than aggregating existing resources as-is, QIMMA applies a multi-model assessment pipeline combining automated LLM judgment with human review...
Algebraic Diversity: Group-Theoretic Spectral Estimation from Single Observations
arXiv:2604.03634v1 Announce Type: new Abstract: We prove that temporal averaging over multiple observations can be replaced by algebraic group action on a single observation for second-order statistical estimation. A General Replacement Theorem establishes conditions under which a group-averaged estimator from...
Improving Feasibility via Fast Autoencoder-Based Projections
arXiv:2604.03489v1 Announce Type: new Abstract: Enforcing complex (e.g., nonconvex) operational constraints is a critical challenge in real-world learning and control systems. However, existing methods struggle to efficiently enforce general classes of constraints. To address this, we propose a novel data-driven...
CoALFake: Collaborative Active Learning with Human-LLM Co-Annotation for Cross-Domain Fake News Detection
arXiv:2604.04174v1 Announce Type: new Abstract: The proliferation of fake news across diverse domains highlights critical limitations in current detection systems, which often exhibit narrow domain specificity and poor generalization. Existing cross-domain approaches face two key challenges: (1) reliance on labelled...
Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensus
arXiv:2604.03809v1 Announce Type: new Abstract: Multi-agent LLM committees replicate the same model under different role prompts and aggregate outputs by majority vote, implicitly assuming that agents contribute complementary evidence. We embed each agent's chain-of-thought rationale and measure pairwise similarity: across...
Self-Execution Simulation Improves Coding Models
arXiv:2604.03253v1 Announce Type: new Abstract: A promising research direction in enabling LLMs to generate consistently correct code involves addressing their inability to properly estimate program execution, particularly for code they generate. In this work, we demonstrate that Code LLMs can...
Automated Conjecture Resolution with Formal Verification
arXiv:2604.03789v1 Announce Type: new Abstract: Recent advances in large language models have significantly improved their ability to perform mathematical reasoning, extending from elementary problem solving to increasingly capable performance on research-level problems. However, reliably solving and verifying such problems remains...
When Adaptive Rewards Hurt: Causal Probing and the Switching-Stability Dilemma in LLM-Guided LEO Satellite Scheduling
arXiv:2604.03562v1 Announce Type: new Abstract: Adaptive reward design for deep reinforcement learning (DRL) in multi-beam LEO satellite scheduling is motivated by the intuition that regime-aware reward weights should outperform static ones. We systematically test this intuition and uncover a switching-stability...
Delayed Homomorphic Reinforcement Learning for Environments with Delayed Feedback
arXiv:2604.03641v1 Announce Type: new Abstract: Reinforcement learning in real-world systems is often accompanied by delayed feedback, which breaks the Markov assumption and impedes both learning and control. Canonical state augmentation approaches cause the state-space explosion, which introduces a severe sample-complexity...
From Plausible to Causal: Counterfactual Semantics for Policy Evaluation in Simulated Online Communities
arXiv:2604.03920v1 Announce Type: new Abstract: LLM-based social simulations can generate believable community interactions, enabling ``policy wind tunnels'' where governance interventions are tested before deployment. But believability is not causality. Claims like ``intervention $A$ reduces escalation'' require causal semantics that current...
LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering
arXiv:2604.03532v1 Announce Type: new Abstract: Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult. Representation-level steering addresses this by adding language-specific vectors to model activations at inference time, but identifying language-specific...
SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression
arXiv:2604.03258v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated impressive capabilities across various tasks, but the billion-scale parameters pose deployment challenges. Although existing methods attempt to reduce the scale of LLMs, they require either special hardware support or...
Announcing the ICML 2026 Workshops and Affinity Workshops