arXiv AI
Jun 30
Selective Memory Retention for Long-Horizon LLM Agents
arXiv:2606. 29178v1 Announce Type: new Abstract: When does retention matter for memory-augmented LLM agents?
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Jun 30
PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents
arXiv:2606. 29225v1 Announce Type: new Abstract: LLM agents handle user requests on behalf of organizations through tool calls and must follow the company policies stated in their system prompts.
arXiv AI
Jun 30
Multi-Agent Routing as Set-Valued Prediction: A WildChat Benchmark and Cost-Aware Evaluation
arXiv:2606. 28925v1 Announce Type: cross Abstract: Tool and agent routing from natural-language prompts is naturally a set-valued prediction problem: a single query may require multiple agents, while over-selection increases execution cost.
arXiv AI
Jun 30
SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance
arXiv:2606. 30113v1 Announce Type: cross Abstract: Discrete action tokenization provides a compact interface for autoregressive VLA policies, but accurately recovering continuous robot actions from discrete codes remains challenging.
arXiv Machine Learning
Jun 30
FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks
arXiv:2606. 28962v1 Announce Type: cross Abstract: Model quantization is essential for the efficient deployment of Large Language Models (LLMs), but introduces a critical vulnerability: Quantization-Conditioned Backdoor (QCB) attacks.
arXiv Machine Learning
Jun 30
Inexact calculus of variations on the hyperspherical tangent bundle with connections to the attention mechanism
arXiv:2507. 15431v4 Announce Type: replace Abstract: We offer a theoretical mathematical background through Lagrangian optimization on the unit hyperspherical manifold and its tangential structure.
arXiv AI
Jun 30
RiverONE: Generating Knowledge-Intensive VLM by Simulated Quantum Machines
arXiv:2606. 29966v1 Announce Type: cross Abstract: Quantum computing provides a powerful paradigm for representing and transforming high-dimensional information through superposition, entanglement, and measurement-induced nonlinear features.
arXiv AI
Jun 30
Transformer Architectures as Complete Bayes Processes: A Formal Proof in the Measure-Theoretic Kernel Framework
arXiv:2606. 30440v1 Announce Type: cross Abstract: We present a complete formal proof that transformer architectures, when their internal update mechanisms satisfy a Bayes joint-distribution condition, implement exact Bayesian posterior inference.
arXiv Machine Learning
Jun 30
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
arXiv:2606. 29526v1 Announce Type: new Abstract: Reinforcement learning (RL) has gained growing attention in large language model (LLM) post-training, yet RL training remains fragile and can suffer from instability or collapse.
arXiv Machine Learning
Jun 30
Reproducing FACTER: Fairness via Conformal Thresholding and Prompt Repair
arXiv:2606. 28620v1 Announce Type: cross Abstract: Fayyazi et al.
arXiv AI
Jun 30
Most Current Model Organisms Are Leaky: Perplexity Differencing Often Reveals Finetuning Objectives
arXiv:2605. 00994v2 Announce Type: replace-cross Abstract: Finetuning can significantly modify the behavior of large language models, including introducing harmful or unsafe behaviors.
arXiv AI
Jun 30
SCRIBE: Diagnostic Evaluation and Rich Transcription Models for Indic ASR
arXiv:2605. 20712v2 Announce Type: replace-cross Abstract: Automatic speech recognition replaces typing only when correction costs less than manual entry - a threshold determined by error types, not counts: fixing a misrecognized domain term costs far more than inserting a comma.
arXiv AI
Jun 30
SFBench: The SciFy Scientific Feasibility Benchmark
arXiv:2606. 29630v1 Announce Type: new Abstract: We present SFBench, a benchmark dataset for evaluating systems that assess the feasibility of scientific claims.
arXiv AI
Jun 30
Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
arXiv:2602. 13562v2 Announce Type: replace-cross Abstract: While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures.
arXiv AI
Jun 30
MedCase-Structured: A Text-to-FHIR Dataset for Benchmarking Diagnostic Reasoning in Clinically Realistic EHR Settings
arXiv:2605. 30295v2 Announce Type: replace-cross Abstract: Large language models (LLMs) show promise for clinical reasoning and decision support, but evaluation in realistic, electronic health record-congruent settings remains limited.
arXiv AI
Jun 30
To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation
arXiv:2606. 29481v1 Announce Type: cross Abstract: While reinforcement learning (RL) significantly enhances LLM reasoning, its efficacy is severely undermined by Pre-RL data overlap, where RL datasets overlap with pretraining or SFT corpora, causing models to exploit shortcuts by memorizing correct answers and fabricating post-hoc reasoning.
arXiv AI
Jun 30
Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game
arXiv:2606. 28456v1 Announce Type: cross Abstract: LLMs agents are increasingly used in multi-agent settings, yet their behaviour in sustainability games remains largely unexplored.
arXiv AI
Jun 30
CytoCLIP: Learning Cytoarchitectural Characteristics in Developing Human Brain Using Contrastive Language Image Pre-Training
arXiv:2601. 12282v2 Announce Type: replace-cross Abstract: The functions of different regions of the human brain are closely linked to their distinct cytoarchitecture, which is defined by the spatial arrangement and morphology of the cells.
arXiv AI
Jun 30
The CRISTAL Method: Neurosymbolic analysis from AI-synthesized world models
arXiv:2606. 29799v1 Announce Type: new Abstract: This project introduces the CRISTAL Method (Coherent Reliable Intentional Synthesis of Truthful Analysis Logic), a neurosymbolic framework for automating complex analysis workflows, with fundamental investment analysis as a primary use case.
arXiv AI
Jun 30
CLQT: A Closed-Loop, Cost-Aware, Strategy-Consistent Benchmark for Diagnostic Evaluation of LLM Portfolio-Management Agents
arXiv:2606. 29771v1 Announce Type: new Abstract: LLM agents are increasingly cast as autonomous portfolio managers, and benchmarks have moved from financial question-answering to sequential trading.