30
Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization
Researchers release OR-Clarify, a benchmark testing whether LLM agents ask clarifying questions before formulating optimization models from incomplete requests.
OR-Clarify evaluates pre-formulation clarification in operations research: each task gives a partial problem description, withholds structured hidden slots, and scores agents via bounded interaction with a simulated user, measuring slot recovery, stopping behavior, silent assumptions, and interaction cost. The authors also propose InterOPT, a two-stage framework that identifies formulation-critical gaps to decide when to ask or stop. In choice-based experiments InterOPT substantially outperforms all baselines in exact slot recovery and remains competitive in the open-ended setting.
35
Import AI 470: No rights for machines; automating environment generation with SPADE; and building better GPU kernels with Hawkeye
METR analysis finds AI accelerating cyber vulnerability discovery, while SPADE self-play environment generation improves Qwen3 reasoning benchmark scores at 30B scale.
Import AI 470 discusses a METR research note reporting differential acceleration from AI: major acceleration in reported cyber vulnerabilities (cURL, OpenSSL, Firefox, Microsoft, NVD, OSV), minor acceleration in mathematics, and no measurable acceleration in AI-research optimization benchmarks. It also covers SPADE, a self-play framework from a multi-university team (University of Washington, Stanford, MIT, CMU, and others) that co-evolves executable training environments and agent capability using Environment Designer and Reasoning Agent roles with hint-based regret rewards. Trained on Qwen3-4B-Instruct-2507, Qwen3-8B, and Qwen3-30B-A3B-Instruct-2507 via GRPO (400 rollouts of 25 environments), SPADE lifted the 30B-A3B game-environment suite average to 58.3, +8.1 over base, and improved tool-use results across backbones. The issue also references Hawkeye for building better GPU kernels.
42
Silver Rate Is (Almost) Optimal for Gradient Descent Acceleration
New optimization theory paper proves near-optimal lower bounds for gradient descent with predetermined stepsizes, confirming silver-schedule optimality.
The paper studies the limits of accelerating gradient descent using predetermined nonnegative stepsizes in smooth convex optimization, with the key constant p_sil = log2(1 + sqrt(2)). It proves a non-anytime lower bound of Omega(n^(-p_sil - O(sqrt(log log n / log n)))) on the error achievable by any such stepsize schedule. In the anytime setting, it shows every infinite nonnegative schedule must incur error Omega(n^(-2*p_sil/(1+p_sil) - O(sqrt(log log n / log n)))) at infinitely many horizons. Combined with the silver-schedule upper bound of Altschuler and Parrilo (2025) and the anytime upper bound of Zhang et al. (2025), these results determine the optimal polynomial convergence exponents in both settings.
28
FlashVector: Agent for Hierarchical Model Serving Stack Optimization
FlashVector agent optimizes all layers of Unity's ad-serving stack, delivering up to 2x model-server throughput and 1.98x latency speedup in production.
FlashVector is an agentic system that optimizes performance across GPU kernels, ML framework computation graphs, model servers, and on-demand feature processing. Deployed in Unity's Vector advertising platform, it achieved up to 2x model-server throughput increase, 1.98x latency speedup, and 1.6x feature-store throughput gain. Optimizations spanned NVIDIA Triton's C++ codebase and the Python feature transformation service, demonstrating extensibility beyond single-kernel tuning.
30
Training a 3.8B LLM to 0.384 CORE for $998 – Hugo Vergnes
Independent developer Hugo Vergnes trained a 3.8B-parameter Llama-style model to 0.384 CORE on 65B tokens for $998 in 43 hours on rented B200s.
Hugo Vergnes trained little-lm, a 3.848B-parameter decoder-only LLM, on 65.3B tokens in 43 hours for $998 using rented NVIDIA B200s, scoring 0.384 on the CORE benchmark and beating nanochat d32 (0.310) at similar cost. The Llama-style architecture uses RMSNorm, RoPE, GQA with 24 query and 8 KV heads, relu-squared MLPs, QK-norm, and ResFormer-style value embeddings that account for 19% of parameters. Key wins included the Muon optimizer for matrix parameters, a trapezoidal learning-rate schedule with linear cooldown, FP8 training plus vocabulary padding for roughly 33% throughput gains, and the ClimMix dataset over FineWeb-Edu. The project, inspired by Karpathy's nanochat, was built as a config-driven YAML framework for small LLM training.
35
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization
COBRA-Skills uses contextual bandits to guide LLM agent skill evolution, cutting optimization cost 55-58% versus SkillOpt while topping six agent benchmarks.
COBRA-Skills formulates LLM agent skill optimization as budgeted sequential optimization over a dynamically evolving candidate space. It couples contextual-bandit-guided prioritization with evidence-grounded skill evolution, selectively spending execution-based evaluations on promising candidates while refining skills from feedback. Across six heterogeneous agent benchmarks and three target models, it achieves the strongest average performance while reducing optimization cost by 55-58% relative to SkillOpt using only 50 unique optimization examples per benchmark. The method remains robust to agent harness changes and works when the target model generates its own skills.
30
When Does Scale-Invariant Optimization Become Unstable? An Exact Schedule Law with Weight Decay
Researchers derive an exact law linking learning-rate schedules and weight decay in normalized networks, pinpointing when scale-invariant optimization destabilizes.
The paper shows that normalization makes large parts of neural networks scale-invariant, creating a hidden feedback loop where learning-rate schedules and weight decay interact through the parameter norm to control the effective optimizer step. An exact discrete-time law with a single scalar quantity separates contraction- and expansion-dominated effective learning-rate regimes, and the balance point is intrinsically unstable, so constant learning rate with weight decay produces recurrent behavior instead of a stable equilibrium. A unified homogeneous-optimizer framework explains why adaptive methods stabilize more weakly under normalization. The law is validated with high precision on MLPs, CNNs, and GPT-2 across MNIST, CIFAR, WikiText, and OpenWebText, with code released on GitHub.
30
AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems
AgentGrad introduces intervention-guided prompt optimization for LLM multi-agent systems, achieving state-of-the-art results with 2.5x faster optimization.
AgentGrad is a prompt optimization framework for LLM-based multi-agent systems that addresses limitations in textual gradient extraction and aggregation. It uses sequential intervention to identify the agent whose prompt modification resolves a given failure, then applies agent-level supervision and semantic gradient clustering to build generalized gradients. Experiments report state-of-the-art performance across five MAS benchmarks and a 2.5x average reduction in wall-clock optimization time versus the next-fastest baseline.
32
Reduced-Space Multi-Fidelity Bayesian Optimization of Process Simulation Models
RS-MFBO couples global sensitivity analysis with fidelity-augmented Gaussian processes to slash costly high-fidelity simulation runs in industrial flowsheet optimization.
The paper presents RS-MFBO, a reduced-space multi-fidelity Bayesian optimization framework for high-dimensional, expensive black-box functions. It integrates Global Sensitivity Analysis for dimensionality reduction with a fidelity-augmented Gaussian process and a cost-aware acquisition strategy featuring cooldown and promotion mechanisms. Validation on a plasmid DNA bioprocess (SuperPro Designer) and a green fuel synthesis plant (Aspen HYSYS) shows substantial reductions in high-fidelity evaluations while remaining competitive with single-fidelity baselines.
15
Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport
Researchers introduce model-aware diffusion schedules via fiberwise optimal transport, cutting flow-matching FID on CIFAR-10 by 38.6% at 16 function evaluations.
The paper proposes constructing diffusion and flow-matching sampling schedules from a fiberwise prediction risk defined via optimal transport, combined with coefficient-path kinetic action, yielding a closed-form time allocation. Across DDPM and flow-matching experiments spanning targets, datasets, and architectures, the schedules beat model-agnostic baselines, including a 38.6% relative FID reduction for flow matching on CIFAR-10 at 16 function evaluations. Normalized fiberwise-risk profiles from independently trained models align closely, suggesting empirical universality, and a frozen analytic allocation template retains most of the gains.
32
Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport
OptiFlow learns one-step multimodal flow policies for offline RL via state-wise entropic optimal transport, avoiding critic overestimation and mode collapse.
The paper introduces OptiFlow, a framework that frames one-step flow policy learning as a structured sample-allocation problem in offline reinforcement learning. It jointly trains a value-aware reference flow policy and a one-step policy, coupling action samples through state-wise entropic optimal transport where critic values set distillation priority and action-distance cost ensures geometrically compatible pairings. By avoiding direct critic maximization, it anchors the policy to high-value dataset-supported modes without out-of-distribution divergence. Code is released on GitHub and the method performs strongly across diverse offline RL benchmarks.
14
30
Bridging the Gap Between Homogeneous and Heterogeneous Asynchronous Optimization Is Surprisingly Difficult
Lower bounds show heterogeneous asynchronous optimization cannot match homogeneous rates under standard similarity assumptions; strong interpolation plus local PL condition closes the gap.
The paper examines whether pessimistic optimal time complexities for asynchronous distributed optimization with heterogeneous workers (different data distributions) can be overcome. It proves improvement is provably impossible under widely used first- and second-order similarity assumptions for any randomized algorithm, and that the weak interpolation assumption alone is also insufficient. Combining strong interpolation with the local Polyak-Lojasiewicz condition yields a new time complexity bound matching the best-known homogeneous dependence on worker computation times without requiring identical data distributions.
10
Bellman Policy Optimization
Bellman Policy Optimization, a critic-free RLVR method derived from Policy Mirror Descent, improves LLM mathematical reasoning without intermediate state-value estimation.
The paper introduces Bellman Policy Optimization (BPO), a critic-free reinforcement learning method for LLMs with verifiable rewards, derived from Policy Mirror Descent. BPO uses the Bellman equations to reformulate PMD as a trajectory-level objective for autoregressive generation with terminal rewards, avoiding state-value estimation at intermediate states. The authors prove BPO shares the same unique optimal solution as PMD and validate it on mathematical reasoning benchmarks.
38
Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models
Drift-Constrained Optimization reformulates fine-tuning as update-direction selection, letting Qwen3 models improve target tasks within a behavioral drift budget.
The paper specifies a behavioral drift budget before optimization and shows that update direction is the remaining degree of freedom, reformulating fine-tuning as a direction-selection problem. In a stringent QA-only setting where instruct models must still generate multi-step reasoning at inference, a coarse layer-selective probe reverses the failure of QA-only fine-tuning. Across Qwen3-8B and Qwen3-14B, these directions substantially improve scientific reasoning and multilingual translation, matching or outperforming dedicated translation systems over 100+ languages and giving stronger initialization for reinforcement learning.
48
Near-Optimal Reinforcement Learning with Multi-Step Transition Lookahead
Theorists prove multi-step lookahead RL planning is NP-hard for every fixed rational discount factor yet give a randomized polynomial-time approximation scheme.
The paper resolves open questions about reinforcement learning with multi-step transition lookahead. It shows exact planning remains NP-hard for every fixed rational discount factor in (0,1), not just discounts arbitrarily close to one, and introduces a randomized polynomial-time approximation scheme for every fixed lookahead depth. Extending to unknown transitions and stochastic rewards via optimism and variance-adaptive confidence bounds, the algorithm achieves cumulative regret matching classical tabular discounted RL up to logarithmic factors.
22
30
30
Robust Policy Optimization via Adversarial Importance Sampling
Adversarial Importance Sampling estimates worst-case RL returns without extra interactions; authors also release the advrl PyTorch library.
The paper introduces Advis, which uses importance sampling over trajectories from standard training to estimate and optimize verifiable worst-case returns, requiring no additional environment interactions or auxiliary networks. It also releases advrl, a modular PyTorch library of single-file robustness methods and adversarial attacks for reproducible evaluation. The authors show adversarial hyperparameters do not transfer across agents, so they evaluate with 6-14x more attacker configurations than prior work. Effectiveness is demonstrated on continuous control environments.
20
Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?
Researchers release Phi-Bench, a benchmark evaluating frontier LLMs on open-ended, long-horizon engineering and optimization of the LLM infrastructure stack.
Phi-Bench evaluates LLMs on open-ended engineering of the LLM infrastructure stack, derived from optimization problems studied in frontier research and grounded in real-world code repositories. Tasks range from localized kernel-level function completion to long-horizon implementation and end-to-end system optimization. Experiments on frontier LLMs reveal current capabilities and limitations on the path toward autonomous optimization of future AI infrastructure.
28
Difficulty-Adaptive Tree-Structured Policy Optimization for Expanding Reasoning Coverage in RLVR
Researchers propose DATPO, a difficulty-adaptive tree-structured RLVR training method that expands reasoning coverage (pass@k) and improves test-time scaling on math benchmarks.
The paper identifies three rollout design principles for RLVR: difficulty-adaptive rollout expands pass@k, tree-based rollout beats parallel sampling, and sentence-entropy-guided forking overcomes token-level branching localization. DATPO combines difficulty-adaptive tree search with a sibling-diversity advantage term to promote semantic diversity during training. On mathematical reasoning benchmarks, DATPO outperforms baselines in pass@k, directly translating to superior test-time scaling performance.
30
PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization
PLC-DPO corrects noisy preference labels during DPO by routing each pair as clean, flip, or tie using calibrated policy-reference margins.
PLC-DPO addresses reversed, weak, or ambiguous preference labels in Direct Preference Optimization by using the calibrated policy-reference margin as online evidence to route each pair's training signal as clean, flip, or tie. This actively corrects supervision direction and strength rather than only filtering suspicious examples. Across 57 dataset-model-benchmark cells, PLC-DPO achieves the best mean win rate of 60.5 versus 55.5 for the next-best method. Injected-noise and tie stress tests plus human disagreement analysis show the routing stays stable and distinguishes flipped from weakly directional pairs.
28
Measuring benchmark optimization in speech recognition
Hugging Face examines how much speech recognition systems overfit benchmarks and how to measure benchmark optimization in ASR.
A Hugging Face post on measuring benchmark optimization in automatic speech recognition, analyzing how model improvements on benchmarks reflect genuine capability gains versus overfitting. It is evaluation methodology research with no direct security impact.
22
30
30
Bridging Control, Inference, Transport, and Thermodynamics: From Theory to Applications in Learning
Review connects control theory, optimal transport, probabilistic inference, thermodynamics, and machine learning via free-energy optimization under constraints.
The review unifies five fields: control theory, optimal transport, probabilistic inference, non-equilibrium thermodynamics, and machine learning. The common conceptual thread is optimization of free-energy-like functionals under dynamical or statistical constraints. Selected applications are presented in reinforcement learning, variational inference, and generative modeling. The tutorial-style text assumes no prior familiarity and begins from physics principles.
15
Why don't machine learning research agents overfit?
Amazon researchers explain why ML research agents avoid benchmark overfitting, attributing generalization to compressibility of successful strategies.
Amazon Science summarizes the paper "What fits (into few tokens) doesn't overfit: Compression and generalization in ML research agents," which investigates why benchmark hill-climbing loops, whether run by human communities or LLM research agents, do not produce rampant overfitting. The explanation formalizes Occam's razor via a counting argument: successful ML strategies are highly compressible, so short descriptions lack room to memorize benchmark data and must capture real structure. LLM-based agents, being resettable and controllable, allow this hypothesis to be tested empirically.
Hacker News · security32
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
SAS trains a gated sparse attention selector end-to-end with the language modeling loss, beating distillation-based sparsifiers on reasoning, long-context, and agentic tasks.
The paper proposes Simple Attention Sparsification (SAS), which injects a selector's continuous scores into attention softmax logits so the language modeling loss directly optimizes context ranking instead of distilling dense attention distributions. Key design choices include log-form gates inside the softmax, normalized gates calibrated against the current block, and preserved continuous selector scores. A memory-efficient Triton kernel integrates SAS into FlashAttention-style computation for long-sequence training. SAS outperforms trainable sparse attention baselines across budgets, with the largest gains under tight attention budgets.
35
A positive resolution of the gap-entropy conjecture
New proof resolves the gap-entropy conjecture for Gaussian bandits, bounding optimal best-arm identification samples by H(log(1/delta)+Ent(I)) up to constants.
A paper proves the gap-entropy conjecture for fixed-confidence best-arm identification with independent unit-variance Gaussian arms, means in [0,1], and a unique optimal arm. It shows the optimal expected sample count, averaged over arm-label permutations, is within absolute constant factors of H(log(1/delta)+Ent(I)), where H sums squared gaps and Ent(I) is the instance's gap-entropy. It also gives an instance-independent algorithm bounded by a constant multiple of this quantity plus a g^-2 loglog(e^e/g) term for the smallest gap g.
15
Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation
Researchers propose ERPO, enabling test-time reinforcement learning for code generation via probe-executed consensus rewards, rank masking, and entropy regularization.
The paper introduces probe-driven test-time reinforcement learning (TTRL) for code generation, where output-free probe inputs are constructed from problem statements and candidate programs are executed on them to compute a Probe Consensus Reward (PCR). Because PCR can be gamed through spurious consensus, the authors propose Entropy-Regularized Rank-Masked Policy Optimization (ERPO), which turns low-PCR outcomes into conservative negative updates via rank masking and constrains policy drift with an entropy ceiling. On coding benchmarks, ERPO substantially improves pass@1 and pass@k in both in-domain adaptation and zero-shot transfer.
38
Optimal Rates for Agentic Networked Information Aggregation
Researchers close the Kearns–Roth–Ryu gap for agentic networked information aggregation, proving excess error is constant up to depth M^2 then Θ(M^2/D).
The paper studies a networked learning model where agents in a DAG each see only a subset of features and pass only their predictions forward. It sharpens the earlier lower bound to Ω(√(M/D)) for depth below M^2 and constructs M-covered paths of depth D ≥ M^2 achieving Ω(M^2/D) excess error, establishing the correct rate for both regression and logistic classification. It also shows excess error contracts geometrically along the path for any fixed distribution, ruling out a single instance that witnesses polynomial lower bounds at every depth.
28
Learning Sparse Decision Trees via Transformer Variational Auto-Encoders
TREVIS uses a Tree Transformer VAE latent space to learn decision trees matching near-optimal predictive performance while improving structural sparsity.
TREVIS learns decision trees optimized for complex objectives by exploring the latent space of a Tree Transformer Variational Auto-Encoder (TTVAE). Mapping trees to continuous latent representations replaces the discrete search space with a continuous one, enabling gradient-based optimization through a differentiable surrogate model. Experiments show TREVIS matches the predictive performance of near-optimal algorithms while improving structural sparsity, targeting high-stakes contexts needing transparent decision logic.
18
30
30
5 useful things you'll learn in my new post-training textbook (shipping now!)
Nathan Lambert's new RLHF and post-training LLM textbook covers PPO, GRPO, GSPO, CISPO and related techniques, freely available online.
Nathan Lambert's book 'Reinforcement Learning from Human Feedback: Aligning and Post-training LLMs' is now shipping from Manning. It covers policy-gradient algorithms including PPO, GRPO, GSPO, CISPO, and RLOO, plus loss aggregation, truncated importance sampling, asynchronous RL systems, and post-training topics like rejection sampling, outcome reward models, and on-policy distillation. The book is freely available online with a 12-hour course, codebase, and exercises.
28
30
30
CMA-OT: Hierarchical Expert Supervision for Dance-to-Music Generation
CMA-OT aligns a music generator's latent features with hierarchical expert representations via curriculum learning and scale-aware optimal transport, improving dance-to-music quality.
CMA-OT introduces curriculum-guided multi-scale representation alignment with scale-aware optimal transport for dance-to-music generation. An external music expert provides hierarchical supervision over the generator's latent features, progressively transferring musical knowledge for stable representation learning. The optimal transport mechanism handles temporal mismatch and semantic variation across expert scales. Experiments on two datasets show state-of-the-art rhythmic synchronization, perceptual quality, and overall music generation.
5
AdamX: Cosine similarity meets gradient descent
Researchers propose AdamX, a cosine-similarity-based first-order optimizer with variance rectification that matches Adam-class convergence across benchmark datasets and architectures.
The paper introduces AdamX, a first-order optimizer that uses cosine similarity as an adaptive mechanism for controlling update magnitudes, plus a variance rectification scheme for smoother optimization early in training. The method is described as scalable, model-agnostic, and straightforward to integrate into existing pipelines. Empirically, AdamX shows competitive convergence rates measured by epochs to reach performance thresholds under a fixed hyperparameter budget, with code and experiments released on GitHub.
22