Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2608.21946v1 Announce Type: cross Abstract: Reinforcement learning with outcome-based objectives such as GRPO enables LLM-based agents to solve complex, long-horizon tasks, yet the reusable exp...
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...
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.
CausalSmith is a framework that automates theoretical research in causal inference by integrating a Lean proof assistant with a self‑improving agentic pipeline. It uses Causalean, a Lean library of over 7,000 machine‑checked declarations, and a pipeline that selects topics, proposes results, formalizes statements, constructs proofs, and audits them against informal claims. The system’s artifacts and source code are publicly available on GitHub.
arXiv:2601.19066v3 Announce Type: replace-cross Abstract: Bug Reproduction Tests (BRTs) have been used in many Automated Program Repair (APR) systems, primarily for validating fixes and aiding fix ge...
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...
The paper introduces PM4Bench, a multimodal, multilingual, multi-task benchmark built on a strictly parallel 10‑language corpus, allowing fair cross‑lingual comparison of Large Vision‑Language Models (LVLMs). It also proposes a vision setting that embeds textual inputs directly into images to better mimic real deployment scenarios. Experiments show OCR performance drives cross‑lingual gaps, leading to an OCR‑centric GRPO training strategy that improves multilingual VQA and reduces disparities without costly supervision.
arXiv:2608.22799v1 Announce Type: cross Abstract: We present the NeuralNexus Arm, an open, low-cost 6-DOF robotic manipulator built by an undergraduate engineering team, together with the design deci...
arXiv:2608.22266v1 Announce Type: new Abstract: In the context of information seeking, conversational agents are undergoing an evolution from reactive tools to proactive, personalized assistants. A c...
arXiv:2608.22762v1 Announce Type: new Abstract: Knowledge graph question answering (KGQA) is a key task for evaluating KG-augmented Large Language Models (LLMs), and complex KGQA that requires multi-...
The paper explores remaining useful life (RUL) estimation using multimodal large language models (MLLMs) that are grounded through time‑series retrieval. It proposes a framework that retrieves historically similar degradation segments, combines them with the test trajectory into a visual comparison artifact, and processes this via a structured multimodal prompt. Experiments on the FD001 partition of the C‑MAPSS benchmark show that retrieval consistently improves RUL prediction, with greater benefits for larger MLLMs, while also revealing current limitations in practical prognostics and health management (PHM) settings.
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:2608.21460v1 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...
arXiv:2608.23067v1 Announce Type: new Abstract: Agent Skills are reusable procedural modules that are increasingly injected into coding-agent sessions to encode framework conventions, anti-patterns,...
arXiv:2608.10503v2 Announce Type: replace Abstract: As Large Language Models (LLMs) are increasingly deployed as autonomous agents, accurately evaluating their latent values and biases is critical. T...
arXiv:2608.22026v1 Announce Type: new Abstract: Accurate simulation of the long-time evolution of systems governed by partial differential equations (PDEs) is central to scientific computing. Among e...
ST‑EVO is a new framework for Large Language Model‑powered Multi‑Agent Systems that introduces a spatio‑temporal evolution of communication topologies. It uses a flow‑matching based scheduler to enable dialogue‑wise communication scheduling and incorporates uncertainty perception and self‑feedback to refine its scheduling over time. Experiments on nine benchmarks show that ST‑EVO outperforms existing methods, improving accuracy by roughly 5% to 25%.
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:2608.22444v1 Announce Type: new Abstract: The unit of AI safety evaluation is still the individual model, yet language-model agents are increasingly deployed in interacting populations that rea...
arXiv:2608.23318v1 Announce Type: new Abstract: Hint-based reinforcement learning addresses reward sparsity in long-horizon agentic tasks by retaining a prefix of an expert trajectory before each rol...