arXiv:2605.06445v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents demonstrate strong performance in autonomous code generation under loose specifications. However, productio...
Tool Calling and Structured Output are two core capabilities of modern Agent systems, yet their interaction under joint deployment conditions remains insufficiently understood. This paper reports a reproducible phenomenon observed in a production Agent system: when Tool Calling and JSON Schema constraints are simultaneously enabled, multiple open-weight models cease invoking tools despite maintaining high schema compliance.
SemVerBench is a benchmark that evaluates how well large language models (LLMs) understand and apply version-constraint resolution semantics, such as determining whether a version satisfies constraints like ^1.2.3 or >=2.0. The study finds that many models struggle with certain corner cases, with GPT‑5.1 performing poorly while Claude and Opus perform much better. The authors suggest that the failures stem from an activation/application gap rather than a lack of knowledge, and recommend that coding agents delegate version resolution to a dedicated resolver tool.
arXiv:2605. 27898v2 Announce Type: replace Abstract: As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential.
arXiv:2604. 13097v3 Announce Type: replace-cross Abstract: Embodied agents increasingly rely on modular capabilities that are installed, upgraded, composed, and governed at runtime, yet the interfaces between these modules are specified only at the level of message types, so integration failures surface only during execution.
Spec‑Harness evaluates how well large language models (LLMs) synthesize Java Modeling Language (JML) specifications by measuring behavioral adequacy across precondition and postcondition correctness and completeness. The study shows that while prompt optimization can raise verifier pass rates, many accepted specifications remain behaviorally weak, either over‑ or under‑constraining inputs and outputs. Spec‑Harness also serves as a feedback mechanism that improves the quality of specifications generated by general‑purpose coding agents and a specialized JML agent.
The paper introduces Pufibara, an agent harness designed to maintain engineering state and evidence across revisions in Modelica-based physical system modeling. It also presents a 232-task Modelica Agent Workflow Benchmark covering model repair, generation, and tuning, evaluated by an external benchmark-owned evaluator. Experiments show Pufibara outperforms Claude Code in task success and resource efficiency across two LLM backends.
arXiv:2606. 00308v1 Announce Type: cross Abstract: Large-language-model code generation has shifted from single-shot prompting to multi-agent orchestrations - analyst, coder, tester, and debugger pipelines - and is evaluated almost exclusively on functional correctness.
UniACE is a unified framework that standardizes the evaluation of large language model (LLM) agents by representing each benchmark as an instruction–tool–environment triplet and running models through a shared, task‑agnostic harness in isolated runtimes. It preserves native success criteria, offers an offline mode for dynamic‑resource tasks, and standardizes efficiency metrics, execution records, and failure attribution. Applying UniACE to 7 benchmarks across 24 domains and 15 models revealed significant score shifts, ranking reversals, and sensitivity to evidence representation, highlighting the impact of evaluation configuration on reported agent performance.
arXiv:2608. 02639v1 Announce Type: cross Abstract: Production prompts rarely carry a single instruction.
arXiv:2607. 14989v1 Announce Type: cross Abstract: Large language models are increasingly evolving from text generators into general agents capable of understanding user requests, invoking external tools, and completing complex tasks through interaction.
arXiv:2608.21208v1 Announce Type: cross Abstract: This paper investigates cross-agent specification portability using Oracle-to-PostgreSQL migration as a controlled software transformation task. The...