arXiv AI
Architecture as Capability Equalizer for Coding Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Jun 24
Constraint Tax in Open-Weight LLMs: An Empirical Study of Tool Calling Suppression Under Structured Output Constraints
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.
arXiv AI
Jul 3
A Unified Framework for the Evaluation of LLM Agentic Capabilities
arXiv:2605. 27898v2 Announce Type: replace Abstract: As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential.
arXiv AI
Jul 3
ECM Contracts: Contract-Aware, Versioned, and Governable Capability Interfaces for Embodied Agents
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.
arXiv AI
4d ago
Beyond Executable Models: The Pufibara Agent Harness and the Modelica Agent Workflow Benchmark for Physical System Modeling
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 AI
Jun 2
How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval
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.
arXiv AI
Aug 5
Instruction Stacking Collapse: A Benchmark and the Capability-Dependent Value of Prompt Compilation
arXiv:2608. 02639v1 Announce Type: cross Abstract: Production prompts rarely carry a single instruction.