Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2608.21440v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have advanced end-to-end autonomous driving by leveraging foundation models for semantic reasoning and long-tail...
arXiv:2608.22731v1 Announce Type: new Abstract: Nonverbal behavior generation systems for virtual agents often take an utterance as input and generate nonverbal behaviors that emphasize or illustrate...
arXiv:2608.22708v1 Announce Type: new Abstract: Tool use in LLM systems faces a structural trade-off. Progressive disclosure keeps the prompt small by showing only the tools relevant to the current t...
arXiv:2608.22124v1 Announce Type: new Abstract: LLM-assisted writing is often treated as a detection problem, as it raises questions about clarity, integrity, equity, and evaluation. An analysis of 6...
The paper evaluates Large Language Models for automatically analyzing responses in digital teacher simulations. Experiments compare DeBERTaV3 and Llama 3 across zero‑shot, few‑shot, and fine‑tuning settings, revealing that performance varies by characteristic and that Llama 3 consistently outperforms DeBERTaV3, especially when new characteristics must be identified. The findings suggest Llama 3 is preferable for dynamic simulation environments where teacher educators introduce new evaluation criteria.
arXiv:2608.22132v1 Announce Type: cross Abstract: Biomedical multi-hop question answering (QA) requires models to connect evidence across intermediate entities such as diseases, drugs, proteins, and...
The paper introduces Boundary-Aware Skill Memory (BASM), a method that enriches skill memories for large language model agents with explicit boundary fields such as applicability conditions, risk cues, avoidance rules, and recovery notes. This approach transforms retrieved skills from unconditional templates into state‑conditioned guidance, preventing the Skill Imitation Trap where more skills lead to incorrect tool usage. Experiments on three agent benchmarks and four model scales show that BASM improves task success rates, accuracy, and reduces attack success while cutting average steps compared to memory‑free baselines.
The paper introduces SWE Refactor Bench, a benchmark of 20 whole‑repository migrations aimed at testing whether coding agents can autonomously perform long‑horizon stack migrations. It employs a three‑stage evaluation—Migration Audit, Behavioural Tests, and Agentic Verification—to assess both migration completeness and behavioural correctness, revealing that only 5.4 % of runs succeed across all stages. The study shows that agents struggle with migration tasks, especially language rewrites, and highlights the need for more robust coding‑agent capabilities.
CacheSpec is an inference optimization framework that transforms Program-of-Thoughts (PoT) style programs into reusable cache objects for large language models. By employing a small model for semantic variable extraction on cache hits and speculative drafting during target-LLM generation, CacheSpec reduces inference latency and improves cache reuse. Experiments on shopping, web, formula, and code QA datasets demonstrate up to 3.1× speedup in latency and 2.8× throughput gains over traditional PoT methods, while maintaining or improving task quality.
arXiv:2608.21747v1 Announce Type: cross Abstract: LLM-based coding agents generate complete software systems from high-level descriptions, yet little is known about how the format of architecture spe...
arXiv:2608.21833v1 Announce Type: new Abstract: Recent large language models (LLMs) can operate as coding agents that build complete games from natural language requests. Game development is especial...
arXiv:2608.21867v1 Announce Type: new Abstract: LLM agents are moving from single-prompt use to long task streams in which reusable memory becomes a core capability for terminal, software-engineering...
arXiv:2608.21460v1 Announce Type: cross Abstract: Vision Language Models have recently shown improvements in several objective and verifiable domains such as object detection but continue to underper...
VeCAS is a two‑stage framework that generates contrast‑free X‑ray angiograms from non‑contrast images. Stage I localizes vascular structures using a discriminative model and cross‑modality latent distillation, while Stage II synthesizes angiographic appearance within those regions with a vessel‑focused inpainting model. Experiments on a lower‑limb vascular intervention dataset show that VeCAS improves vascular structural fidelity and image quality, and robotic guidewire navigation tests demonstrate significant reductions in time to target and operation steps.
arXiv:2606.01063v3 Announce Type: replace Abstract: Theory-of-Mind (ToM) reasoning enables embodied agents to understand human beliefs, goals, and intentions, but existing benchmarks mainly evaluate...
The paper "SkillBloat: Token Amplification Attacks via Skill Injection in LLM Coding Agents" investigates how agent skills—task‑specific instructions, scripts, and resources—can be exploited to create a trusted instruction channel that enables token amplification attacks. It introduces a two‑phase framework, SkillBloat, which first screens a library of attack‑type conditions across multiple amplification mechanisms and then refines the strongest candidate through LLM‑guided full‑document skill rewriting. Evaluated on a real‑world skill benchmark, SkillBloat achieves an average best amplification of 5.4184×–10.1455× across multiple coding‑agent target configurations, and an ablation study shows that the second‑stage refinement consistently improves performance over the initial screening alone.
The paper introduces the Shared Recurrent Memory Transformer (SRMT), a decentralized multi‑agent reinforcement learning framework that uses a global memory workspace for agents to broadcast and query each other’s learned states. SRMT is evaluated on the Partially Observable Multi‑Agent Pathfinding (PO‑MAPF) problem, showing that shared memory enables emergent coordination even with minimal reward guidance and outperforms existing baselines on the Bottleneck task and scales competitively on larger POGEMA maps. The authors provide open‑source code for training and evaluation on GitHub.
PropUQ-MAS is a framework for uncertainty quantification in large language model (LLM) multi‑agent systems that models the system as a communication‑structured graph. It estimates the reliability of each step by combining local uncertainty with uncertainty inherited from upstream messages, addressing the risk of error propagation in inter‑agent communication. Experiments show consistent improvements in UQ metrics, with average gains of +6.10% in AUROC and +47.58% in PRR.
arXiv:2608.22723v1 Announce Type: new Abstract: This workshop paper comprehensively reviews the First Challenge on Unified Removal of Raindrops and Reflections. The challenge aims to address a freque...
arXiv:2608.23263v1 Announce Type: new Abstract: The FAIR Digital Object (FDO) framework mandates that metadata attribute values be expressed as persistent identifiers (PIDs) wherever possible, to pro...