We study a governed approach to enterprise analytics: a language model interprets the question, while deterministic policy selects and runs a pre-approved analytical program that returns both results and evidence. We show that this restriction can remain expressive within a defined analytical class, using relational operations plus aggregation, comparison, windows, ranking, and similarity. Fixed meaning, policy, data, and execution rules also make results replayable. Across 440 runs, three 8B models generated SQL and selected tools at runtime, while Qwen3-8B interpreted intent only and policy executed the approved program. None of 330 runtime-planning episodes matched the full answer-and-evidence contract across all test datasets; the policy-executed analyzer matched 110 of 110. This is a configuration-specific result, not evidence that runtime agents cannot succeed under other designs.
CrisBench, a 1,200-question benchmark of lifecycle reasoning that combines a controlled formal setting with programs executed against Cordis, a runtime that manages component dependencies and cleanup, and asks models to identify affected components, predict state after a specified teardown order, and determine which co...
Guardrails for tool-using LLM agents are usually application-specific rules, which makes multi-step, data-dependent safety policies hard to specify, audit and reuse. As a declarative alternative, we evaluate metric first-order temporal logic (MFOTL), replaying the recorded trajectories that AgentDojo, STAC and R-Judge...
Nikolaos Kekatos, Stylianos Basagiannis, Marinelio Chintri et al.· Proceedings of the 2026 8th...· 2 citations
STAGE, an executable-graph framework that confines model judgment to policy-scoped nodes while placing procedural control in deterministic code, improves task success and repeated-run reliability compared with monolithic full-policy execution.
Mengxi Luo, Changjiao Chen, An Cao et al.· 1 citation
RADAR is an auditable runtime that makes an agent's analytical choices inspectable and supports their revision through execution feedback and rejects the operation or provides diagnostic feedback, allowing the agent to revise its choices before errors propagate.
Han-Xu Yan, Lang-Xuan Deng, Zheng-Le Wang et al.· 0 citations
Agent frameworks can persist checkpoints, trace tool calls, and limit resource use, but these facilities often assign different identities to execution, governance, and replay. We present Pollard, a framework-independent runtime based on governed semantic execution trees. A step identity commits to canonical input, kin...
Metis, a multi-provider runtime that converts provider streams into typed events before admitted calls reach external effects is presented, a multi-provider runtime that converts provider streams into typed events before admitted calls reach external effects.
Jun'an Yu· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.
