Skip to main content
Search

# LLM Agent Workflow

12 related articles

Subscribe to updates
  1. Test cases stop being hand-written one by one: five agents split the work and audit themselves, averaging a 93.4% mutation score across five datasets

    Software test-case design has long depended on manual work, and models that treat generation as one-shot text translation struggle with multi-layered business rules. A pipeline of five roles, parser, triage, architect, writer and auditor, turns test generation into a stateful reasoning process in which the auditor corrects scripts before output. Across five datasets spanning travel, telecom, financial regulation and a government job platform, the pipeline averaged a 93.4% mutation score, 1.4% hallucination and 7.8% redundancy, at an average generation time of 21.2 hours.

  2. Metal printing design stops relying on manual judgment: agents revise the part and the assessment code, cutting a thermal peak by 160 °C

    Design assessment for laser powder bed fusion no longer requires engineers to hand-carry results between preset rules and simulation tools. AgenticDfAM lets language-model agents interpret manufacturing guidance, select tools and propose redesigns, while geometric measurement and numerical comparison stay with executable tools. Across four case studies, three redesign strategies removed all reference violations on an analytical artifact, thermal feedback lowered a bracket's predicted layer-scale peak temperature by 160 °C, and a corrected support-construction procedure was reused in four build orientations.

  3. Claude Platform opens OpenTelemetry export: trace Messages API calls and managed-agent sessions in your own backend

    Claude Platform now exports tracing data for Messages API requests and Claude Managed Agents sessions as OpenTelemetry spans, so developers can view those calls in their own observability backend.

  4. arXiv

    SkillMorph evolves agent skills via trajectory-guided fault localization, raising pass3 on SWE-Skills-Bench from 67.96% to 88.37%

    The work proposes SkillMorph, a skill-evolution approach based on trajectory-guided fault localization: it abstracts raw trajectories into state-transition sequences, aggregates failure and success coverage evidence across repeated runs, evolution loops, and tasks to identify suspicious actions, then traces those actions back to edit sites that may span multiple skills and artifacts before generating revisions; on SWE-Skills-Bench and CannBot the evolved skills achieve higher pass@3, trial-level accuracy, and pass3 than the original skills and four existing skill-evolution methods, and a deployment with an AI operator-development team produced six accepted skill-revision pull requests.

  5. arXiv

    APEX moves indirect prompt-injection defense to the execution boundary, cutting attack success to 0% on five of six benchmarks and 0.56% on the sixth

    The work presents APEX, which shifts indirect prompt-injection defense from recognizing attack patterns to checking each proposed effect at the execution boundary: before untrusted execution it compiles the user's authorization into a contract, WRAP admits an effect only when the contract and runtime evidence reconstruct its authorization, and PLANT places probes on the contract's endorsed dependencies so unendorsed use of runtime information reveals itself before commitment; across six benchmarks and 13 baselines APEX reaches 0% attack success on five benchmarks and 0.56% on the sixth, and holds 0% under three adaptive attacks spanning all three capability-unit types.

  6. arXiv

    PLUTO turns natural-language rendezvous missions into SCP constraints, generating a trajectory for all 50 prompts with 94% passing mission-intent verification

    The work introduces PLUTO, an interactive trajectory design framework that embeds agentic AI coding tools within a sequential convex programming (SCP) architecture, mapping natural-language rendezvous mission requirements into structured mathematical constraints that pass through an auto-convexification pipeline into executable optimal control formulations; across 50 natural-language rendezvous mission prompts spanning 10 constraint types, PLUTO generated a trajectory for every prompt and 94% of the resulting trajectories satisfied both numerical constraint checks and semantic consistency with the original mission intent.

  7. arXiv

    EvoCast separates cognition from authority to evolve forecasting architectures autonomously, reaching the lowest MSE on three real forecasting cases at lower agent-side cost

    EvoCast is a fully autonomous research-agent system for iterative time-series forecasting architecture evolution: it first establishes and diagnoses a task-specific baseline, then generates evidence-grounded research directions from dataset characteristics, diagnostic results, prior rounds, and failure records, with LLM agents handling hypothesis generation and code implementation while deterministic program authorities control source-edit boundaries, canonical evaluation, and model promotion; it reaches 96.7% success on 30 repository-level implementation tasks and the lowest MSE on three real forecasting cases (Air Quality, Melbourne Pedestrian T33, Steel Industry) while using fewer tokens and lower API cost than R&D-Agent.

  8. arXiv

    SHarP prunes agent harness modules by single-module ablation saliency: four harnesses cut token cost by at least 10% at comparable performance, and OpenHands on GAIA rises from 29.44% to 35.00%

    The work proposes SHarP, which treats tools, instructions, and supporting mechanisms in an agent harness as individually disableable modules, estimates each module's performance and efficiency saliency through single-module ablation, and prunes by an efficiency-oriented or performance-oriented rule; across five settings (OpenHands/GAIA, PaperQA2/LitQA2, LIFE-harness airline and retail, JIT agentfold/DeepPlanning-Shopping), most pruned configurations retain comparable performance, all four harnesses achieve at least a 10% token-cost reduction, and two improve task performance while cutting cost.

  9. arXiv

    Foresight lets a frozen Qwen3-VL-8B plan its own future perception in streaming video, reaching 23.0 joint F1 on OmniPro Online and beating the strongest trained baseline by 9.5%

    The authors introduce Foresight, a training-free dual-stream architecture with two Siamese LLMs sharing weights, input encoders, and a KV cache, where one copy continuously ingests the stream while the other runs ahead over the same causal state to write a plan deciding when to reason next, what to check then, and how densely to sample; with a frozen Qwen3-VL-8B backbone it reaches 23.0 mean joint F1 on OmniPro Online (versus 13.5 for the strongest trained baseline, MiniCPM-o 4.5), improves the backbone by 6.7 points on StreamingBench with a best overall score, and by 15.4 points on OVO-Bench, with the largest gain of 18.7 points on Forward Active Responding where evidence arrives later in the stream.

  10. arXiv

    CRAFT fills spreadsheet forms with template-aware reflection and local repair, raising pair accuracy by 8.51 and 23.38 points on FormFillBench

    The authors propose CRAFT, a template-aware agent framework for spreadsheet form filling that couples reflective validation with constrained local repair: it localizes suspicious regions, restores overwritten template content when needed, re-grounds plausible writable slots with a Rectangle-Aware Slot Grounder (RASG), and constrains later edits via label-slot hints and protected regions; they also release FormFillBench with 327 forms across Instruction-Only and Multi-File tracks, where CRAFT improves pair accuracy over the strongest baselines by 8.51 and 23.38 percentage points respectively, with component-removal experiments supporting structural adjudication and slot re-grounding and a second backbone retaining the relative advantage.