A controlled, component-level study (176 settings, 4 models, SWE-Bench Verified + Terminal-Bench 2.1) isolating how context-management strategy, planning, and action-space…
Proposes Self-Retiring On-Policy Distillation, where a skill-conditioned teacher trains jointly with RL and the student adaptively drops the teacher once…
SELF-INDEX lets a retrieval index self-evolve without human intervention: an Optimizer diagnoses retrieval shortfalls and revises the responsible index keys…
EvoSkill-GUI packages GUI-agent skills as structured, multi-file artifacts that get revised at deployment time via a reflect-revise-reuse loop (in-rollout revision,…
A post-training framework (Instance-level Difficulty-Aware Control) that dynamically allocates reasoning depth per-problem via reward shaping, improving AIME24 Pass@3 by 10.0%…
Introduces AMPLE-Math (5,319 problems, six matched reasoning views) to isolate exactly how much a privileged reference solution adds beyond plain…
For a fixed test-time-scaling candidate budget (N=8), splitting generation into more, smaller sequential calls costs 4.64-4.86x more gross GPU energy…
Legal AI startup Harvey raised $550 million in a funding round co-led by Lightspeed Venture Partners and Diffusion, reaching a…
Microsoft has integrated xAI’s Grok models into Copilot for Word, Excel, and PowerPoint through its Frontier Program preview. The rollout…
California Governor Gavin Newsom signed a package of laws described as the nation’s strongest child-safety protections against AI chatbots and…
OpenAI released its Agents API in public beta, giving developers direct access to the managed Codex harness that powers its…
OpenAI CEO Sam Altman said the company will not pursue an initial public offering in 2026, calling it an “ill-advised”…
