Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility
arXiv:2607.14108v1 Announce Type: new Abstract: This paper introduces tool efficiency, a new quantitative metric to evaluate the rate of useful tool calls in an LLM agent…
Latest
MEMORA: Embodied Action Memory from Egocentric Videos for Reasoning and Planning
arXiv:2607.14252v1 Announce Type: cross Abstract: Long-horizon robot planning requires more than predicting what actions will do next; it also requires memory of the embodied experience that…
Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs
arXiv:2607.14107v1 Announce Type: new Abstract: The inference efficiency of diffusion large language models (dLLMs) is constrained by two challenges: bidirectional attention precludes efficient KV-cache reuse, while…
LBA: Textual Hard-Label Adversarial Attack under Low Query Budgets
arXiv:2607.14101v1 Announce Type: new Abstract: Generating high-quality adversarial texts with low query budgets remains a challenging problem in the hard-label scenario. Most existing approaches rely on…
UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure
arXiv:2607.14102v1 Announce Type: new Abstract: With the rapid growth of digital data, real-world applications increasingly involve hierarchical information that combines static attributes with dynamic records. Modeling…
Latent Communication Between Language Model Agents: Channels, Alignment, and the Limits of Text
arXiv:2607.14103v1 Announce Type: new Abstract: Multi-agent systems (MAS) are utilized in many contexts and many professions. Those MAS rely on inter-agent communication, usually implemented by clear-text…
Automatically Evolving Prompt Guidelines for Task-Specific Optimization
arXiv:2607.14105v1 Announce Type: new Abstract: For Large Language Models to reliably answer user queries, users must clearly specify requirements, context, and constraints. In practice, however, user…
UzWordnet and Generative AI for Learning Uzbek by Game Playing
arXiv:2607.14104v1 Announce Type: new Abstract: This paper presents an educational system architecture that enables learners to practice the Uzbek language through game-playing. The architecture integrates UzWordnet…
Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration
arXiv:2607.14399v1 Announce Type: cross Abstract: Evaluations of language-model honesty read the model's verdicts as evidence about the model. We test the instrument instead. We built a…
Token Time Continuous Diffusion for Language Modeling
arXiv:2607.14106v1 Announce Type: new Abstract: In this paper we introduce token time continuous diffusion (TTCD), a new diffusion language model which (a) operates in continuous space,…
MedFailBench: A Clinician-Built Open-Source Benchmark for Medical AI Safety Boundary Inspection
arXiv:2607.15166v1 Announce Type: cross Abstract: Most medical AI benchmarks measure whether a model knows the correct answer. MedFailBench asks a different question: which safety boundary failed?…
Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization
arXiv:2607.14614v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) commonly uses entropy for advantage shaping. However, entropy cannot distinguish useful uncertainty from detrimental confusion,…
Translating Classical Poetry into Modern Prose
arXiv:2606.02806v2 Announce Type: replace Abstract: We introduce Padyam2Gadyam a dataset for the task of poem-to-prose translation from 13th-17th Century Telugu Classical Poetry to contemporary Telugu and…
Idea2Plan: Exploring AI-Powered Research Planning
arXiv:2510.24891v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated significant potential to accelerate scientific discovery as valuable tools for analyzing data, generating hypotheses, and…
Mixtures of SubExperts for Large Language Continual Learning
arXiv:2511.06237v2 Announce Type: replace-cross Abstract: Enabling lifelong learning in LLMs demands resolving the stability-plasticity dilemma (i.e., models must incorporate new knowledge without overwriting prior representations) while…
Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents
arXiv:2607.15263v1 Announce Type: cross Abstract: Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testing, and CTF completion.…
ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System
arXiv:2607.14178v1 Announce Type: new Abstract: Recent advances in Large Language Models have fueled autonomous AI agents capable of tackling complex scientific tasks, yet existing automated research…
Latent Trajectory Discrimination for AI-Generated Text Detection
arXiv:2607.14967v1 Announce Type: cross Abstract: Most existing approaches to AI-Generated Text Detection (AIGTD) treat documents as static objects and base their decisions on aggregate statistics or…
When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models
arXiv:2607.14169v1 Announce Type: new Abstract: Large language models can synthesize a game's rules as executable code - a Code World Model (CWM) - which a classical…
Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality
arXiv:2607.14816v1 Announce Type: cross Abstract: Large Language Models (LLMs) perform differently on identical programming tasks when prompted in different natural languages, a phenomenon known as language…
MemoHarness: Agent Harnesses That Learn from Experience
arXiv:2607.14159v1 Announce Type: new Abstract: An agent harness is the external control layer that turns a base LLM into an executable agent by managing context, tools,…
Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms
arXiv:2607.14607v1 Announce Type: cross Abstract: Machine learning (ML) models deployed in sensitive domains such as healthcare, law enforcement, and finance must satisfy not only utility requirements…
Orchestrating Power Grid Studies with Multi-Agent AI and MCP Servers
arXiv:2607.14158v1 Announce Type: new Abstract: This position paper explores how Agentic AI and Model Context Protocol (MCP) can support power-grid studies in a Transmission System Operator…
MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems
arXiv:2605.28732v3 Announce Type: replace-cross Abstract: Memory is essential for enabling large language models to support long-horizon reasoning, yet existing memory systems remain unreliable and difficult to…