The paper introduces an observable evidence standard to assess whether adding a planning capability in industrial AI systems delivers operational value. By separating opportunity, plan change, consequence, equivalence, uncertainty, and scope, the authors evaluate diverse planning additions on real retail datasets, revealing that composite policies can mask negligible contributions, execution changes may not always yield benefits, and indirect evidence alone cannot fully attribute value. The study demonstrates how this evidence record can guide decisions on validation, deployment, monitoring, redesign, and retirement of planning capabilities.
Industrial artificial intelligence (AI) planning systems combine predictive models, optimization logic, controls, and governance rules, but improvement in the complete policy does not show whether one...
The paper introduces an evidence‑guided recovery framework for AI agents that encounter ambiguous tool outcomes and partial execution, such as timeouts or failures. It defines a shared admissibility check for key expiry, authorization timing, dependencies, and residual effects, and a terminal certificate to distinguish actual goal satisfaction from publicly supported safe completion. In a finite study of 37 assignments, the approach achieved 28 certified completions, and in a larger comparison of 58 paired units, evidence‑guided advice certified 30 completions versus 9 for evidence prompting, demonstrating a significant improvement in task completion rates.
The paper investigates how the distribution of capacity and task information across stages of AI production affects the economic value of inference. Using controlled workflow experiments on software‑engineering tasks, it finds that direct execution achieves a 59.6% success rate at token ceilings of 12,000 and 24,000, while information‑constrained planning improves from 36.2% to 51.2%. The study also shows that giving planners access to task issues boosts success, and that scaling token limits changes the balance between planning and execution workloads.
The paper investigates how agent harnesses—specifically planning guidance, execution organization, and completion verification—affect performance in retail and airline pilot tasks. By comparing fixed, task‑specific plans to shuffled policy text of equal length, the study finds that fixed plans improve success rates by about 7 percentage points, especially on complex tasks. A read‑only verifier rejects a majority of invalid episodes while incurring minimal cost, and its impact varies with the penalty for erroneous acceptance, often matching the full planning‑plus‑verification benefit at a lower cost.
arXiv:2606. 29878v1 Announce Type: new Abstract: Predictive models are increasingly embedded in operational decision-making, yet standard explanation methods typically explain forecasts rather than the decisions those forecasts induce.
Predictive models are increasingly embedded in operational decision-making, yet standard explanation methods typically explain forecasts rather than the decisions those forecasts induce. This distinction is important in predict-then-optimize systems: large forecast changes may leave the optimizer's action unchanged, while small changes can alter the selected decision and its realized value.
The paper introduces a compute‑aware three‑action controller for evaluator‑guided reasoning, deciding whether to trust the current answer, fallback, or expand inference. It scores terminal actions by predicted success and uses a rollout‑based surrogate for expansion, explicitly pricing compute cost. Experiments on width expansion and revision tasks show the controller improves utility over fixed policies while reducing online compute by about 30% and 16%, respectively, and demonstrates that evaluator‑guided reasoning is best viewed as resource allocation under uncertainty.
arXiv:2609.37125v1 Announce Type: new Abstract: Prospective memory allows an agent to retain an intention tied to a future condition, but the stored intention does not reveal whether that condition c...
arXiv:2608. 01548v2 Announce Type: replace Abstract: Language-first intelligence is constrained by which distinctions enter its symbolic record, which mappings its language--interpreter--environment complex can execute, and which possibilities can be realized with finite resources.
arXiv:2608. 00832v1 Announce Type: new Abstract: Structured plan-generation agents are often evaluated as if a plan has quality in isolation, yet many realistic planning tasks require asking how a candidate behaves when another agent can search for responses.
arXiv:2608. 05519v1 Announce Type: new Abstract: Agent benchmarks usually measure task completion and treat resource use as an auxiliary statistic.
arXiv:2608.29560v1 Announce Type: new Abstract: A company with a fixed artificial intelligence (AI) budget must decide which large language model (LLM) handles each recurring workload. What it lacks...