The monograph introduces Elimination Geometry (EG), a typed, native‑loss, audit‑oriented framework that investigates when locally optimal objects can be realized by a shared deployment rule. EG examines how elimination and compression can erase distinctions needed for prediction, inference, control, or representation, and it separates local solvability, global realizability, and finite‑sample certifiability. The work synthesizes tools from geometry, optimization, information theory, statistics, and machine learning to address regular, coordination, singular, compositional, and resource‑limited mechanisms, and demonstrates applications in sparse model selection, distribution‑free prediction, observational treatment policies, routed expert and retrieval systems, and learned score fields.
arXiv:2608. 02712v1 Announce Type: cross Abstract: Kernel generation for hardware accelerators such as GPUs and NPUs has become a proving ground for large language models (LLMs), and state-of-the-art systems raise correctness through pipelines that couple LLMs with agentic reinforcement learning and evolutionary search.
The paper introduces ReviveBench, a benchmark designed to evaluate coding agents’ ability to revive non‑running software and reconstruct industrial engines from open specifications. It comprises two families of tasks—revival (ten tasks addressing dependency issues, missing modules, legacy builds, and GPU models) and reconstruction (thirteen tasks covering numerical, geometric, hardware, and transactional systems). The benchmark uses hidden verifiers calibrated against native environments, engineering tools, or reference implementations, and the authors report that the strongest evaluated model passes all revival tasks and most reconstruction tasks, while also uncovering verifier defects that highlight measurement error in executable verification.
arXiv:2609.05736v2 Announce Type: new Abstract: LLM tool agents can be improved without retraining by modifying the runtime harness around a fixed model: prompts, tool interfaces, middleware, state h...
arXiv:2608. 11079v1 Announce Type: new Abstract: Self-evolving agents accumulate reusable skills by appending successful procedures and failure fixes.
arXiv:2608.11318v2 Announce Type: replace-cross Abstract: Many sequential construction tasks have exact terminal symmetries even though execution is directed and depends on history. Process evidence...
arXiv:2606. 16999v1 Announce Type: cross Abstract: Frozen small code models ( =45.
The paper demonstrates that a verifier used in closed‑loop agent debugging can inadvertently reveal the answer it is meant to test, rendering solver comparisons meaningless. In a study of 12 development cases, both exact minimum hitting set and a greedy method returned identical supports, and an audit showed that exact‑anchor predicates always produced the planted fault pair. The authors propose a support‑gated verification contract that requires a clean reference map and runtime evidence before an independently calibrated signal can confirm a detection, and validate this approach on 1,440 held‑out cases with a low false‑admission rate.
arXiv:2606. 17529v1 Announce Type: cross Abstract: Scientific machine-learning (SciML) surrogates approximate expensive simulations, but exact expected outputs for arbitrary inputs are unavailable (the oracle problem).
arXiv:2607. 22761v1 Announce Type: cross Abstract: Resolving Design Rule Violations (DRVs) in layouts entails an iterative loop of geometric edits and verification.
arXiv:2607. 29431v1 Announce Type: new Abstract: Large language models increasingly generate optimization models from natural language, but existing evaluation often reduces a generated model and its ground truth to a single equivalent/not-equivalent verdict or an execution-success rate--labels that are neither independently checkable nor faithful to the multiple distinct senses in which two formulations can agree.
arXiv:2607. 16632v1 Announce Type: cross Abstract: Hardware engineering exposes coding agents to a form of long-horizon work that is difficult to capture with pass-at-k: progress is continuous, tool feedback is delayed and heterogeneous, and a backend failure may require revising RTL rather than tuning another physical-design parameter.
The paper investigates a failure mode in Graph-JEPA, a joint‑embedding predictive model trained on a large scientific‑reasoning graph. Despite achieving high linear‑probe accuracy and effective rank, the learned representation contains almost no usable instance information, as shown by retrieval metrics. The authors diagnose the issue to variance allocation in the objective, propose a repair that restores near‑perfect information recovery, and demonstrate that the problem persists even after repair, highlighting limitations in the evaluation metrics used.