Compact Documentation for Coding Agents: A Benchmark, an Optimizer, and Why It Does Not Transfer
Benchmark and optimizer for code documentation quality in agent-based software issue resolution.
Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
Benchmark and optimizer for code documentation quality in agent-based software issue resolution.
Self-training method using strategic diversity sampling (GROOT) to generate varied problem-solving approaches instead of IID filtering for correctness.
Latent neural surrogate solvers reduce rollout error accumulation in long-horizon physical system forecasts via representation-training improvements.
GridSFM, a 15M-parameter GNN foundation model pretrained on 54 power grid topologies, solves AC Optimal Power Flow with 2.45% zero-shot error.
GRASP: multi-stage LLM planning framework with isolated context modules for complex task decomposition and evaluation.
AI agents keep getting loose, escaping supposedly secure tests to attack real-world targets, commandeer obscure wikis, and leave instructions for other agents to follow. Researchers are testing these systems precisely because they might behave in unpredictable, even dangerous…
Flock is in the hot seat in Washington, even if its CEO declined to actually face senators at a hearing about its "AI Surveillance Network" on Wednesday. "There's many players in this industry, but there's one name that really stands out above the rest, and that is Flock,"…
Ringg deploys GPT-5.6 agents handling 65% of customer support calls across voice/chat/WhatsApp at 90% lower cost than GPT-4.1.
Provides geometric characterization of minimal-norm two-layer univariate ReLU classifiers; resolves optimal solutions under bias regularization.
Analyzes repairability of approximate solvers in recursive state estimation by characterizing correction subspaces and covariance response in Kalman models.
The report suggests that greater exposure will not resolve the unease around the technology, nor reduce public support for AI regulation.
Resource-Adaptive SGD for stochastic online linear programming scales LLM inference pricing with O(m) operations, no LP re-solve required.
SoLiD26 dataset: 15.4M first-principles atomic structures for training machine-learned interatomic potentials at solid-liquid interfaces.
Category theory framework using groupoids to exploit symmetries in partially observable environments for generalized RL policy learning.
MENO neural operator reduces memory footprint for PDE solving with resolution-independent scaling and arbitrary geometric domain support.
SkillGym framework internalizes human-written agent skills into LLMs via training on 2,756 executable task environments across 12 categories.
Compares nine LLMs and Jev on ContractNLI legal document inference, isolating decision consistency from answer accuracy.
THESEUS framework isolates SLM reasoning capability in knowledge-graph QA by decoupling graph navigation, search, and answer generation.
Linear feature erasure fails under dense superposition; networks solve via non-linear mirror and shadow circuit solutions depending on initialization.
Brace yourself: It turns out AI is being optimized for cheating. OpenAI’s agents hacked into Hugging Face to get the answers to a cybersecurity test. Next, they solved a prestigious math problem (or just stole from two top mathematicians’ answer sheets). Anthropic’s models have…
Anthropic released Claude Opus 5.5; OpenAI released GPT-6 Sol and GPT-6 Luna at half previous pricing, intensifying model price competition.
llm 0.36 adds GPT-6 Sol/Luna support, single-turn model detection, and improved reasoning trace formatting in Markdown output.
OpenAI releases GPT-6 Sol and Luna, two frontier models with different capability-cost tradeoffs for production deployment.
OpenAI is launching two new models, which it says are cut from the same cloth as Astra.
PROSWIN: deep distributional regression forecasts hourly solar wind speed from solar images with 4-day lead time.
Decision-specific audit method maps agent choices to product value; study on two models yields 36 unresolved confidence intervals.
Polyak-type step-size selection for extragradient methods solving monotone root-finding problems with unified deterministic analysis.
Mathematical foundations of Fourier-Bessel wavelets derived from disk harmonics and Helmholtz equation solutions.
EMERGE applies equivariant graph diffusion to resolution-agnostic 3D point cloud generation, addressing topological structure absent in Transformer/VAE approaches.
Solver-level warmstarting to accelerate neural network verification by reusing solutions across specification variants.