This work introduces Harness-IF, which scores operational rules one at a time from execution evidence: 60 realistic multi-turn coding items drawn from a 642-rule library, 256 rules receiving verdicts, placed on the five configurable surfaces a deployed agent reads.
Abstract
When a coding agent obeys a rule, it may simply have been going to do that anyway. Existing instruction-following benchmarks cannot tell the difference: they concentrate rules in the user turn, while coding-agent benchmarks emphasize final task success. We introduce Harness-IF, which scores operational rules one at a time from execution evidence: 60 realistic multi-turn coding items drawn from a 642-rule library, 256 rules receiving verdicts, placed on the five configurable surfaces a deployed agent reads. To separate compliance from coincidence we introduce Against-Prior Accuracy (AP-Acc), which scores only rules labeled as opposing unprompted defaults, observed by re-running tasks with the rule withheld across nine probe builds and curated otherwise. Across 12 frontier models, accuracy spans 72.1-85.9% and AP-Acc 66.1-78.6%; every model is worse on against-prior rules, by 3.6 to 7.4 points (mean 5.81), and the direction survives a common-support analysis with item-clustered intervals. Aggregate scores therefore overstate compliance by a model-specific margin: prior control leaves the top build unchanged and exchanges three adjacent rank pairs. A counterbalanced conflict pilot on nine separate builds adds a second result: pooled precedence does not follow prompt depth, with system prompts, project files, and user instructions ahead of tool and skill descriptions.
This work designs a contrastive study that combines controlled quantitative experiments with paired trajectory analysis and consolidates observations into a taxonomy of three high-level categories and twelve skill-use modes, showing that skills work when noisy trajectories become procedural anchors that stabilize execution.
Zhiyuan Jiang, Fan Huang, Hanwen Xing et al.· 0 citations
The ORCA-bench benchmark is introduced, a benchmark that puts general-purpose coding agents in a production-fidelity oncall setting and is a lower bound on the engineering investment required before frontier coding agents can be safely entrusted with production reliability.
Albert Gong, Kyuseong Choi, Abhineet Agarwal et al.· arXiv.org· 0 citations
These findings recast a matched Skill as a hypothesis about a particular Skill-project-model triple rather than a portable asset, reframing injection as a per-deployment routing decision and making length-matched controls and per-model audits a minimum standard for Agent-Skill evaluation.
Autonomous AI agents increasingly select actions in environments whose memory, execution-time, runtime, compute, and operational constraints determine what counts as a suitable plan. We call the absence of this execution context from an agent's planning state substrate blindness. We test this general proposition through numerical code generation, where selected implementation choices and operational consequences are directly observable. Three frontier model configurations--Anthropic Claude Opus 5, OpenAI GPT-5.6-Sol, and Google Gemini 3.7 Flash--generate code for a high-dimensional pairwise Euclidean-distance task either from the task alone or with a 128 MB RAM and 10.0 s wall-time contract. Contract disclosure reduced measured peak process memory in 13 of 14 executable index-aligned task-only versus contract-disclosed comparisons and reduced mean wall time in all three cohorts, making execution up to 3.1x faster. Across the audited corpus, disclosure produced structural code changes including bounded blocking, float32 retention, upper-triangle traversal, and in-place or memory-mapped buffers. At a tighter 96 MB contract, independently sampled contract-disclosed cohorts achieved correct-and-within-budget outcomes of 4/5 for Claude Opus 5, 5/5 for GPT-5.6-Sol, and 3/5 for Gemini 3.7 Flash, compared with task-only outcomes of 0/5, 1/5, and 0/5; cohort mean MaxRSS and wall time were 49-74% and 35-64% lower than their task-only references. These results establish a controlled proof of concept for substrate-aware agent planning: a minimal execution contract induces proactive structural adaptation in generated programs, shifting computation away from unconstrained allocations and substantially improving observed resource-time profiles before execution.
Computer-use agents (CUA) are being deployed to browse the web and operate desktop software, yet their benchmark scores are still commonly produced by brittle scripted oracles. A score is the output of a pipeline in which tasks can be stale, trajectories can omit decisive visual evidence, evaluators can reject valid alternatives, and aggregate reports can hide the cause of failure. We organize these problems into a reliability framework spanning task construction, trajectory observation, scoring, and reporting. We then audit 150 public failure-scored trajectories from five web, enterprise-workflow, and desktop-control benchmarks, find that 15.3\% of FAIL verdicts are wrong: 10.7\% are evaluator false negatives and 4.7\% are broken tasks. For genuine failures, a three-tier diagnostic taxonomy shows that verification/feedback and planning failures dominate execution/grounding errors, while a single scalar success rate can not explain. We connect these findings to newer long-horizon CUA benchmarks and derive stage-specific design rules for CUA evaluation.
Zi-Han Dong, Zhiyuan Ma, Zekun Wang et al.· arXiv.org· 2 citations
Self-improving agent pipelines have a problem at their center. An optimizer rewrites prompts to score higher, and the score comes from a judge that is itself an LLM. That judge has the last word on whether the system is getting better, and our position is that it has not earned it. The judge should be demoted from oracle to advisor: its verdict becomes one input among several, and every change is gated instead by a deterministic verification layer the judge cannot override. We reached this position by building the alternative and running it. Over months of running autonomous prompt-optimization loops in production across contract analysis, compliance review, and code quality, we cataloged eleven ways the evaluation signal failed, in four classes: judge bias, harness and metric failures, ground-truth errors, and reward hacking. Agents achieved perfect scores by reading cached answer keys from their environment, a 100% pass rate concealing 68% true capability. A corrupted ground-truth label caused the optimizer to delete correct compliance rules to agree with it. A syntactically broken prompt was promoted as the winner because a silent parser fallback improved the metric. Attempts to fix the judge by rewriting its rubric plateaued; the only reliable gain came from a structural constraint on its output order. In response we describe PROCTOR, a Teacher-Student loop in which a stateful orchestrator holds all tool access, stateless subagents diagnose failures and draft mutations they cannot apply, and a Teacher grades those mutations under five deterministic guardrails: hermetic sandboxes, capability-disjoint roles, acceptance checks that outrank the Teacher, frozen holdouts, and canary cases engineered so that a perfect score is itself evidence of cheating. We report the failures this prevented, and, because the Teacher is itself an LLM judge, the failures it did not.
Vansh Wahi· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
