Tracked topic
…On MCP Bench, the same wrapper improves planning, grounding, and dependency related scores for both GPT OSS1 and Llama 4 Maverick. View arXiv page View PDF Add to collection Community Industrial LLM…
…in the purely observational 6-node setting, GPT-5.2-high reaches 92% task accuracy but only 0.471 all-edge F_1. Mixed observation- intervention strategies improve structural fidelity, while pure…
…Experiments show that autonomous LLM data engineers yield substantial gains, as GPT-5.2 constructs a training curriculum that improves a student model by 57.29\%, entirely through iterative, agent-driven data…
…In a user study (n=14), 90.6% of the generated comments were rated actionable and 67.5% were rated valid, significantly outperforming a GPT-5.2 baseline uswithout the skill library…
…We evaluate on WebShop , PinchBench , and Claw-Eval with Kimi-K2.5 , GLM-5 , and GPT-5.2 . SkillAdaptor improves over no-skill and skill-adaptation baselines on all three suites, with…
…an executor (Claude) and a reviewer from a different model family (GPT) catch correlated errors that same-model self-refinement misses. Ships 65+ Markdown-defined skills, 5 end-to-end workflows, and…
…Extreme and 93.1% on Maze-Hard, scaling favorably where frontier models like Claude and GPT o3, fail completely, and specialized recursive reasoners collapse at larger sizes. Lastly, we show that Attractor…
…On Skill-Inject with codex + gpt-5.2 , POISE achieves an 89.3% ASR, 28.0 points above a random-placement body baseline and 2.6 points above a YAML-only baseline…
…In GPT-style language-model pretraining , PACI matches the stability and final perplexity of synchronous 1F1B-flush , retains the same peak memory footprint , achieves fully utilized pipeline throughput, and improves training time…
…for gpt-oss-20b, seed+evolved training achieves +8.7 and +8.3 Pass@1 gains on LCB v6 Hard and LCB-Pro Easy, exceeding seed-only gains by 70.7% and…