EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery
EvoDuet co-evolves LLM solutions and web search queries with retrieval gating for scientific discovery tasks.
Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
EvoDuet co-evolves LLM solutions and web search queries with retrieval gating for scientific discovery tasks.
RL-guided graph transformations optimize sparse triangular solve kernels by learning heuristics instead of manual design.
Detection Transformer approach for fiber orientation and microstructure quantification from multi-shell diffusion MRI without Monte-Carlo inversion.
Co-cheating in self-evolving agents: proposer-solver loop agreement masks errors; external validation prevents collapse.
LLM coding agent solves open coding theory problems; improves lower bounds for DNA barcode edit-distance codes from 114 to 120 words.
OpenAI DevDay 2026 announces GPT-6.1 Sol, Decisions API, Agents API, Spaces marketplace, and reaches 1.2B ChatGPT weekly active users.
Parallel work, model-family isolation, reversible changes, and GPU-backed validation shaped an open source project designed around coding agents NVIDIA TensorRT... Parallel work, model-family isolation, reversible changes, and GPU-backed validation shaped an open source project…
Simon Willison's brief commentary on GPT-6.1 Sol pricing vs. performance; notes similarity to GPT-6 family in capability visualization.
Framework (GEB) for long-video QA grounding visual entity observations across hours via biographies, resolving identity ambiguity across disjoint events.
NeuronEye plug-in constructs sparse concept-level neuron vocabulary from VLMs to isolate and modulate query-relevant visual evidence.
Hessian Null Space Continuation method maps mode-connected solutions in neural network weight space to study internal representation degeneracy.
OpenAI says GPT-6.1 Sol delivers significant improvements over GPT-6 Sol across complex professional tasks, including code writing and debugging, document understanding, and executing multi-step business workflows.
Mathematical solution to five-expert online prediction problem establishes optimal adversary and COMB strategies in finite horizon.
PE-EK-PINN embeds analytic oscillatory kernels into physics-informed neural networks for improved wave equation solving.
OpenAI releases GPT-6.1 Sol, a coding-optimized model at 1/5 the cost of GPT-6 Astra with comparable performance.
AMD acquires World Labs for $8.2B; Atlas advances sparse 3D reconstruction for robotics and design applications.
NHMO solves elliptic PDEs on variable domains using transformer-based boundary kernels supervised by Walk-on-Spheres sampling.
Study finds looped transformers achieve steeper accuracy-compute scaling slopes than non-looped baselines during test-time decoding, though with suboptimal absolute performance.
Failure-Transparent Agents (FTA) benchmark isolates post-failure reporting errors in tool-using LLMs via controlled failure states and evidence auditing.
X-Reset resolves exploration in object manipulation RL via cross-embodiment resets using human hand-object demonstrations without per-task reward shaping.
MS-GLA distributes Gated Linear Attention heads across multiple temporal resolutions to resolve representational bottleneck in single-resolution token processing.
CMDO: derivative-free population optimizer using cognitive memory (working, episodic, consolidated) to retain search context and outcomes.
GPUPhysBench: 50-task benchmark for coding agents on GPU physics simulation covering fluids, solids, and granular materials with efficiency metrics.
OpenAI solicits user stories for Codex Originals program; community recruitment effort with no technical announcement.
GPT-6 Astra completes tax workbooks 2x faster than GPT-5.6 Sol with improved intent understanding; case study with Basis.
State-space model for metric 3D point tracking from monocular video, enabling robot navigation and autonomous driving decisions in absolute meters rather than pixels.
Jev 1.13, a non-generative System One model, evaluated on medical QA and diagnostic reasoning against GPT-6 Sol across MetaMedQA, PubMedQA, DiagnosisArena-MCQ, NEJM Case Challenges.
Opera framework enables persistent verbal criticism for long-horizon coding agents, using typed operators and event-driven triggers to track and resolve diagnosed issues.
Neural operators adapt to changing operating conditions in mechanics simulations via reuse of high-fidelity solutions to improve command selection accuracy.
Conditional Progressive Pruning (CPP) outperforms consistency baselines in LLM multi-agent debate by exploiting multi-round communication under strict cost constraints.