arXiv Machine Learning

Self-Certification of Representation Adequacy: Sequential Certification at Minimum Task Loss

arXiv:2608. 02267v1 Announce Type: cross Abstract: Agents that act on a compressed representation of their history face a structural risk: if the representation aliases histories with different optimal actions, no rule measurable with respect to the representation can avoid an irreducible per-round loss, and the agent may be unable to detect this from its own transcript.

Hugging Face Trending Papers
Aug 3

Self-Certification of Representation Adequacy: Sequential Certification at Minimum Task Loss

Agents that act on a compressed representation of their history face a structural risk: if the representation aliases histories with different optimal actions, no rule measurable with respect to the representation can avoid an irreducible per-round loss, and the agent may be unable to detect this from its own transcript. This paper develops a four-layer theory of self-certification of representation adequacy.

arXiv AI
Jul 20

From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems

arXiv:2607. 15459v1 Announce Type: new Abstract: A trained deep reinforcement learning policy is a black box, and we ask whether it can be made explainable by rewriting it as an executable logic program that reproduces its behaviour and that a person can read, a logic engine can run, and an optimizer can edit.

By Eduardo C. Garrido-Merch\'an
arXiv AI
Jun 30

SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution

arXiv:2606. 29713v1 Announce Type: cross Abstract: Hallucination is the reliability bottleneck for LLM-based agents, and fact attribution verifiers are the last line of defense -- yet today's verifiers emit only opaque binary labels, leaving agents unable to self-correct and operators unable to audit.

By Aojie Yuan, Yi Nian, Haiyue Zhang, Zijian Su, Yue Zhao
arXiv Machine Learning
Aug 11

Finite Constant Frontiers and Auditable Regret Certificates for Average-Reward Reinforcement Learning

arXiv:2608. 07725v1 Announce Type: new Abstract: Average-reward reinforcement-learning regret is known up to logarithmic factors, but the numerical content of published guarantees is difficult to compare because probability mode, structural parameter, logarithmic normalization, prior information, and planning assumptions differ.

By Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Md Najmus Swaqeeb
arXiv Machine Learning
Jul 1

Certified Speculative Execution for Untrusted AI Agents

arXiv:2606. 31023v1 Announce Type: cross Abstract: Hard-constrained sequential decision systems have no certified way to spend the test-time compute of modern AI: executing the multi-step drafts of a learned policy or a frozen LLM forfeits the feasibility guarantee a trusted solver provides, while invoking the solver at every step forfeits the speed the AI offers.

By Chenyu Zhou, Qiliang Jiang, Shuning Wu, Xu Zhou