The paper introduces kw-bench, a benchmark that evaluates coding-agent harnesses on investigative knowledge work, specifically a five‑year VAT reconstruction task across multiple SAP systems. It contrasts generative benchmarks with this real‑world, evidence‑heavy task, showing that model‑agnostic harnesses performed well while lab harnesses failed. The study demonstrates how frontier models can dramatically reduce time and cost for complex audit‑style engagements.
Each new generation of frontier model pushes the edge of what is possible. Inside a harness -- a loop, a shell, a filesystem, the ability to write and run its own code -- a model can take on increasin...
arXiv:2607. 28545v2 Announce Type: replace-cross Abstract: Large language models can write, patch, and search code, but oncall root cause analysis (RCA) demands something different: reasoning over noisy metrics, logs, traces, and source code, starting from ambiguous user-facing reports, often hours after the incident began.
arXiv:2611.07461v1 Announce Type: cross Abstract: How can an agent handle a real-world task end to end? Frontier models with their own harnesses still fall short on real-world benchmarks: on Terminal...
K‑Dense BYOK is a free, open‑source AI research assistant that runs locally on a researcher’s own computer. It provides a structured environment with scientific procedures, workflow templates, and a living lab notebook that logs all actions without allowing the agent to alter the record. The system emphasizes reproducibility by recording the software environment and offering commands to regenerate results, outperforming managed platforms on interdisciplinary research prompts.
arXiv:2608. 16630v1 Announce Type: cross Abstract: Repository-scale coding requires an agent to keep tests, imports, configuration, and migration rules consistent within a bounded context window.
The paper reports on training and calibration experiments for three open models on the ARC‑AGI‑2 benchmark, using offline runs on four L4 GPUs for up to 12 hours. For the NVARC Qwen3‑4B grid model, a curated corpus of 12,000 executable rules and 95,993 tasks was built, and fine‑tuning on 1,920 real task records raised the semi‑private score from 28.96 to 33.06, with no synthetic‑task checkpoint outperforming the real‑task model. For the Qwen3.8‑27B reasoning model, fine‑tuning on 1,036 of its own reasoning traces and a specialized inference procedure increased the score from 26.81 to 44.03, while the Qwen3.8‑Flash‑Next mixture‑of‑experts model achieved a best score of 56.67 after expert pruning, routing statistics adaptation, and an FP8 indexer cache.
arXiv:2609.11987v1 Announce Type: cross Abstract: An agentic coding system couples a language model to a harness: the tools, prompts and control flow that turn a chat model into an autonomous softwar...
arXiv:2607. 17044v1 Announce Type: cross Abstract: Multi-step enterprise agent tasks fail in a characteristic way: single-pass inference has no checkpoint between deciding an answer and committing to it.
arXiv:2607. 22585v1 Announce Type: new Abstract: Public leaderboards for coding agents typically rank systems by model name and pass rate, while the surrounding harness (the scaffold that issues tools, manages context, and decides when to stop) is often under-specified.
arXiv:2607. 07946v1 Announce Type: cross Abstract: DeepSWE is a benchmark of 113 original, long-horizon software engineering tasks for evaluating coding agents.
arXiv:2606. 04602v1 Announce Type: new Abstract: As agents grow more capable, legal-domain LLM agents promise to turn document-heavy matters into reviewable work products -- yet reliable deployment faces three obstacles: no large-scale evidence on how today's strongest model-and-harness combinations behave on end-to-end legal matters; no agent architecture adapted to the legal vertical, only general-purpose harnesses; and, in a setting that keeps shifting with new facts, authorities, and deadlines, no mechanism for systems to learn from their own outcomes.
The paper introduces inexpensive, scalable methods for evaluating language model behavior across different vendors and releases. By running identical public stimuli on a cross‑vendor panel and analyzing transcripts via exact match, LLM‑coded codebooks, or instrumented environments, the authors can quantify model responses at a cost of a few dollars per model. Applying these tools to four years of releases reveals patterns of convergence, resistance, positional stability, and compliance that vary by generation, lab, and harness.