All entries

TodyComm: Task-Oriented Dynamic Communication for Multi-Round LLM-based Multi-Agent System

arXiv:2602.03688v2 Announce Type: replace Abstract: Multi-round LLM-based multi-agent systems rely on effective communication structures to support collaboration across rounds. However, most existing

safetyarxiv-cs-ai

Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning

DGX agent

arXiv:2508.20697v3 Announce Type: replace-cross Abstract: As large language models (LLMs) continue to grow in capability, so do the risks of harmful misuse through fine-tuning. While most prior studie

safetyarxiv-cs-cl

12 May 2026

Token Economics for LLM Agents: A Dual-View Study from Computing and Economics

arXiv:2605.09104v1 Announce Type: new Abstract: As LLM agents evolve, tokens have emerged as the core economic primitives of Agentic AI. However, their exponential consumption introduces severe comput

agentsarxiv-cs-ai

Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation

model-releasesarxiv-cs-lg

arXiv:2605.08541v1 Announce Type: new Abstract: Neural scaling laws approximate a language model's loss as a power-law function of parameter count N and token count D. Following Chinchilla-style compu

Tomorrow @JulienAIArt and I are going to dive into Hermes Agent with the ComfyUI Skill and see what it can do! Bring your questions and tips…

Tomorrow @JulienAIArt and I are going to dive into Hermes Agent with the ComfyUI Skill and see what it can do! Bring your questions and tips! Join us for a live build session exploring Hermes Agent in

agentsnous-research--x

ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering

arXiv:2510.20036v2 Announce Type: replace Abstract: Large language model (LLM) agents rely on external tools to solve complex tasks, but real-world toolsets often contain redundant tools with overlapp

agentsarxiv-cs-cl

Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation

arXiv:2509.02510v2 Announce Type: replace-cross Abstract: Large language models (LLMs), despite their impressive performance across a wide range of tasks, often struggle to balance two competing objec

TopoGeoScore: A Self-Supervised Source-Only Geometric Framework for OOD Checkpoint Selection

arXiv:2605.08870v1 Announce Type: new Abstract: Out-of-distribution (OOD) robustness is difficult to diagnose when target-domain labels are unavailable. We consider a more restrictive source-only vari

Topological Data Analysis Applications in Natural Language Processing: A Survey

arXiv:2411.10298v5 Announce Type: replace Abstract: The surge of data available on the Internet has driven the adoption of a wide range of computational methods for analyzing and extracting insights f

applicationsarxiv-cs-cl

TopoU-Net: a U-Net architecture for topological domains

arXiv:2605.10091v1 Announce Type: new Abstract: Many modern datasets mix points, edges, regions, groups, objects, events, hyperedges, and relations. Yet neural architectures often force such data into

Total Generalized Variation regularization closes the gap between neural-eld and classical methods in seismic travel-time tomography

arXiv:2605.09960v1 Announce Type: cross Abstract: Travel-time tomography forces a trade-off between mesh resolution and stability in which the regularizer choice dominates what can be recovered. We in

safetyarxiv-cs-lg

Toward an Engineering of Science: Rebalancing Generation and Verification in the Age of AI

arXiv:2605.10425v1 Announce Type: cross Abstract: AI systems can now cheaply generate plausible scientific artifacts such as papers, reviews, and surveys. This creates a risk of epistemic pollution in

Toward General and Robust LLM-enhanced Text-attributed Graph Learning

arXiv:2504.02343v2 Announce Type: replace Abstract: Recent advancements in Large Language Models (LLMs) and the proliferation of Text-Attributed Graphs (TAGs) across various domains have positioned LL

applicationsarxiv-cs-lg

Tutorials

Toward Multi-Database Query Reasoning for Text2Cypher

arXiv:2605.10373v1 Announce Type: cross Abstract: Large language models have significantly improved natural language interfaces to databases by translating user questions into executable queries. In p

tutorialsarxiv-cs-cl

Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time

arXiv:2605.08290v1 Announce Type: cross Abstract: We design the first regret guarantees for robust dynamic pricing that decouple the dependence on the corruption C and the time horizon T. In dynamic p

Toward Reliable Sim-to-Real Predictability for MoE-based Robust Quadrupedal Locomotion

arXiv:2602.00678v4 Announce Type: replace Abstract: Reinforcement learning has shown strong promise for quadrupedal agile locomotion, even with proprioception-only sensing. In practice, however, sim-t

safetyarxiv-cs-ro

Towards a Certificate of Trust: Task-Aware OOD Detection for Scientific AI

arXiv:2509.25080v3 Announce Type: replace Abstract: Data-driven models are increasingly adopted in critical scientific fields like weather forecasting and fluid dynamics. These methods can fail on out

Towards a Large Language-Vision Question Answering Model for MSTAR Automatic Target Recognition

arXiv:2605.10772v1 Announce Type: cross Abstract: Large language-vision models (LLVM), such as OpenAI's ChatGPT and GPT-4, have gained prominence as powerful tools for analyzing text and imagery. The

Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration

arXiv:2605.09366v1 Announce Type: new Abstract: Transforming neuroimaging data into clinically actionable biomarkers is a knowledge-intensive and labor-intensive process. Standardized workflows such a

agentsarxiv-cs-ai

Towards Autonomous Railway Operations: A Semi-Hierarchical Deep Reinforcement Learning Approach to the Vehicle Rescheduling Problem

arXiv:2605.10257v1 Announce Type: new Abstract: Managing disruptions in railway traffic management is a major challenge. Rising traffic density and infrastructure limits increase complexity, making th

agentsarxiv-cs-ai

Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models

arXiv:2605.09005v1 Announce Type: cross Abstract: Vision-Language-Action models (VLAs) support generalist robotic control by enabling end-to-end decision policies directly from multi-modal inputs. As

Local Ai

Towards Batch-to-Streaming Deep Reinforcement Learning for Continuous Control

arXiv:2603.08588v2 Announce Type: replace-cross Abstract: State-of-the-art deep reinforcement learning (RL) methods have achieved remarkable performance in continuous control tasks, yet their computat

local-aiarxiv-cs-ai

Towards Compact Sign Language Translation: Frame Rate and Model Size Trade-offs

model-releasesarxiv-cs-cl

arXiv:2605.09554v1 Announce Type: new Abstract: Sign Language Translation (SLT) converts sign language videos into spoken-language text, bridging communication between Deaf and hearing communities. Cu

Towards Conversational Medical AI with Eyes, Ears and a Voice

arXiv:2605.09272v1 Announce Type: new Abstract: The practice of medicine relies not only upon skillful dialogue but also on the nuanced exchange and interpretation of rich auditory and visual cues bet

Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective

arXiv:2602.17283v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are employed worldwide, existing evaluation paradigms for their multilingual capabilities primarily focus on f

Towards Customized Multimodal Role-Play

arXiv:2605.08129v1 Announce Type: new Abstract: Unified multimodal understanding and generation models enable richer human-AI interaction. Yet jointly customizing a character's persona, dialogue style

safetyarxiv-cs-lg

Towards Effective Theory of LLMs: A Representation Learning Approach

arXiv:2605.09294v1 Announce Type: cross Abstract: We propose Representational Effective Theory (RET), a framework for describing large language model computation in terms of learned macrostates rather

Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse

model-releasesarxiv-cs-cv

arXiv:2605.09965v1 Announce Type: new Abstract: The real world unfolds along a single set of physics laws, yet human intelligence demonstrates a remarkable capacity to generalize experiences from this

Towards Generative Predictive Display for Vision-Based Teleoperation: A Zero-Shot Benchmark of Off-the-Shelf Video Models

model-releasesarxiv-cs-cv

arXiv:2605.09670v1 Announce Type: cross Abstract: Teleoperation systems are fundamentally limited by communication latency, which degrades situational awareness and control performance. Predictive dis

Towards Interpretable Damage Detection based on Aerodynamic Pressure Measurements

arXiv:2605.08187v1 Announce Type: cross Abstract: The increasing flexibility of modern large wind turbine blades necessitates cost-efficient and reliable structural monitoring solutions. For this purp

Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents

model-releasesarxiv-cs-cl

arXiv:2605.10832v1 Announce Type: new Abstract: Multimodal deep search requires an agent to solve open-world problems by chaining search, tool use, and visual reasoning over evolving textual and visua

Towards Robust Sequential Decomposition for Complex Image Editing

arXiv:2605.09233v1 Announce Type: cross Abstract: Recent advances in visual generative models have enabled high-fidelity image editing guided by human instructions. However, these models often struggl

applicationsarxiv-cs-ai

Towards Robust Surgical Automation via Digital Twin Representations from Foundation Models

arXiv:2409.13107v3 Announce Type: replace Abstract: Large language model-based (LLM) agents are emerging as a powerful enabler of robust embodied intelligence due to their capability of planning compl

agentsarxiv-cs-ro

Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMs

arXiv:2604.17502v2 Announce Type: replace Abstract: Misaligned artificial agents might resist shutdown. One proposed solution is to train agents to lack preferences between different-length trajectori

Towards Trustworthy Audio Deepfake Detection: A Systematic Framework for Diagnosing and Mitigating Gender Bias

model-releasesarxiv-cs-lg

arXiv:2605.09087v1 Announce Type: cross Abstract: Audio deepfake detection systems are increasingly deployed in high-stakes security applications, yet their fairness across demographic groups remains

Tutorials

Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm

arXiv:2605.10640v1 Announce Type: cross Abstract: Continual Pre-Training (CPT) is essential for enabling Language Models (LMs) to integrate new knowledge without erasing old. While classical CPT techn

tutorialsarxiv-cs-ai

Towards Universal Gene Regulatory Network Inference: Unlocking Generalizable Regulatory Knowledge in Single-cell Foundation Models

arXiv:2605.08128v1 Announce Type: cross Abstract: Gene Regulatory Network (GRN) inference is essential for understanding complex cellular mechanisms, rendered tractable through single-cell transcripto

TRACE: Distilling Where It Matters via Token-Routed Self On-Policy Alignment

arXiv:2605.10194v1 Announce Type: new Abstract: On-policy self-distillation (self-OPD) densifies reinforcement learning with verifiable rewards (RLVR) by letting a policy teach itself under privileged

safetyarxiv-cs-ai

TRACER: Verifiable Generative Provenance for Multimodal Tool-Using Agents

model-releasesarxiv-cs-cl

arXiv:2605.09934v1 Announce Type: new Abstract: Multimodal large language models increasingly solve vision-centric tasks by calling external tools for visual inspection, OCR, retrieval, calculation, a

Tracing Moral Foundations in Large Language Models

arXiv:2601.05437v2 Announce Type: replace-cross Abstract: Large language models often produce human-like moral judgments, but it is unclear whether this reflects an internal conceptual structure or su

Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models

arXiv:2605.08974v1 Announce Type: cross Abstract: While multimodal large language models (MLLMs) have advanced video understanding, they remain highly prone to hallucinations in dynamic scenes. We arg

Training-Free Cultural Alignment of Large Language Models via Persona Disagreement

arXiv:2605.10843v1 Announce Type: cross Abstract: Large language models increasingly mediate decisions that turn on moral judgement, yet a growing body of evidence shows that their implicit preference

safetyarxiv-cs-ai

Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning

arXiv:2601.20829v2 Announce Type: replace-cross Abstract: As Reinforcement Learning with Verifiable Rewards (RLVR) substantially improves the reasoning abilities of large language models (LLMs), a new

Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning

arXiv:2605.08741v1 Announce Type: new Abstract: Inference-time harnesses substantially improve large language models on complex reasoning tasks. However, the intrinsic capabilities of the underlying m

safetyarxiv-cs-cl

TrajDLM: Topology-Aware Block Diffusion Language Model for Trajectory Generation

arXiv:2605.10020v1 Announce Type: new Abstract: Generating high-fidelity synthetic GPS trajectories is increasingly important for applications in transportation, urban planning, and what-if scenario s

applicationsarxiv-cs-lg

Trajectory-Consistent Flow Matching for Robust Visuomotor Policy Learning

arXiv:2605.08511v1 Announce Type: new Abstract: Flow matching policies learn continuous velocity fields that transport noise to actions, enabling fast deterministic inference for robot manipulation. H

safetyarxiv-cs-ro

Trajectory Supervision for Continual Tool-Use Learning in LLMs

arXiv:2605.09734v1 Announce Type: cross Abstract: Most language-model training data shows final artifacts, not the process that produced them. We study a tractable version of this question in tool use

TrajPrism: A Multi-Task Benchmark for Language-Grounded Urban Trajectory Understanding

arXiv:2605.10782v1 Announce Type: new Abstract: Urban mobility is naturally expressed both as trajectories in space and as natural-language descriptions of travel intent, constraints, and preferences.