Deep equilibrium models promise input-adaptive implicit computation: harder problems should demand more solver iterations, and the solved equilibrium should encode the result of genuine iterative inference. We report a cautionary study of a port-Hamiltonian DEQ with a learned initialization on two reasoning tasks -- ProofWriter entailment over frozen DeBERTa embeddings and a BFS-verified graph-reachability benchmark -- in which the implicit computation is a silent no-op.
arXiv:2607. 11116v1 Announce Type: cross Abstract: Deep equilibrium models promise input-adaptive implicit computation: harder problems should demand more solver iterations, and the solved equilibrium should encode the result of genuine iterative inference.
By Joyjeet Singh
The paper investigates why reinforcement learning with verifiable rewards (RLVR) reduces the diversity of solutions in reasoning tasks. By analyzing the Countdown task, the authors show that RLVR contracts the solution space mainly at the entrance—before the first arithmetic operation—causing a 67% drop in solution coverage. They demonstrate that providing an unselected entrance prefix or applying entrance‑targeted interventions can restore or even improve coverage without harming accuracy.
By Qiancheng Zhou, Ruizhe Li
arXiv:2602. 05463v2 Announce Type: replace-cross Abstract: Modern AI systems achieve remarkable capabilities at the cost of substantial energy consumption.
By Koichi Takahashi, Yusuke Hayashi
arXiv:2605. 24033v2 Announce Type: replace Abstract: Mechanistic interpretability typically discovers circuits and then argues what they do from examples and ablations.
By Neel Somani
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
arXiv:2608. 12700v1 Announce Type: new Abstract: Systems that generate GPU kernels with language models report high correctness rates.
By Rishi Shah, Rishav Shrestha
The paper introduces the Infinity Machine, a self‑improving AI agent designed to solve research problems whose solutions can be programmatically verified. The system operates autonomously: it generates candidate solutions, verifies them, and audits the results without human intervention, all within a sandboxed environment governed by a kernel‑enforced gate. In a six‑day experiment, the Infinity Machine achieved four new state‑of‑the‑art results in quantum information and improved qubit‑routing and hardware efficiency, while also documenting several failure modes.
By Harish Santhanalakshmi Ganesan
The paper introduces entry-state sharpening, a data‑free pre‑training step that prepares a language model’s checkpoint in a sharper, lower‑entropy state before test‑time reinforcement learning (TTRL). By reducing policy entropy, the model can more efficiently use its limited adaptation budget, leading to higher endpoint conversion efficiency across tasks such as MATH, GPQA, and AMC. Experiments with different data‑free objectives (e.g., R‑Zero vs. SPIRAL) demonstrate that the choice of pre‑training objective strongly influences the checkpoint’s readiness for TTRL, and a label‑free self‑distillation intervention can further sharpen the entry state.
By Zhanming Zhang, Vinoth Selvendran
The paper investigates how the dynamical regime of recurrent-depth reasoners—whether they settle, drift, or remain marginal—affects the reliability of test‑time depth. It establishes a depth‑safety condition based on per‑step displacement relative to the decoder margin, showing that operators in a settling regime can safely increase depth without degrading performance and can even improve accuracy on harder unseen tasks such as Sudoku. The authors provide empirical evidence from algorithmic tasks trained on limited data, demonstrate the impact of a terminal fixed‑point objective on depth behavior, and offer operational criteria to identify useful test‑time depth while cataloguing failure modes.
By Ivan Viakhirev, Kirill Borodin, Amirah Almutairi, Serguei Barannikov, Maxim Abramov, Grach Mkrtchian
arXiv:2609.37351v1 Announce Type: cross
Abstract: Test-time compute scaling has emerged as a cornerstone of advanced machine reasoning, yet performing iterative deliberation directly within continuou...
By Zeyu Jia (School of Biomedical Engineering,Technology, Tianjin Medical University, Medical School, Tianjin University)
The paper investigates how to allocate test‑time computation in recursive reasoning models, specifically the Tiny Recursive Model (TRM). Experiments show that resampling the answer state (y) is more effective than perturbing the reasoning state (z) for recovering failures, especially as compute budgets increase. The proposed Gated Answer Resampling (GAR) method, which restarts only rejected puzzles, boosts TRM performance from 85.9% to 99.4% on Sudoku‑Extreme and from 68.8% to 85.6% on the Pencil Puzzle Bench, outperforming the probabilistic variant that uses far more compute.
By Maxime Illouz