The main barrier for AI agents in production is shifting from model capability to fragmented knowledge, decision reliability, and dynamic evaluation. Static benchmarks are failing to capture multi-turn, tool-using agent behavior.
Mirror Particle is launching at TechCrunch Disrupt Startup Battlefield with a world model built from scratch to predict human behavior, arguing that LLM roleplay falls short for market research and brand strategy. AI-RADAR links this move to the grow...
MIT Technology Review Insights surveyed 300 executives and found that only 34% of agentic AI projects reach production. The root cause is not model capacity but fragmented data, legacy systems, and weak semantic context. Production leaders show stron...
An executable benchmark for Chinese chess shows that LLM agents can point to the right move and still lose. Across 119 tactical endgames, 8,568 multi-turn trajectories and 12 frontier LLMs, closed-loop success collapses compared with static evaluatio...
A paired evaluation across 11 decision points for LLM agents finds hosted Jev outperforms open-weight Laya on 9 tasks, but neither beats chance on zero-shot routing. The pipeline audit turns a claimed 23.9% saving into an actual 4.3%.
Observational world models are not enough for modular LLM agents: a sequence does not say whether payment authorizes shipment or a hidden factor explains both. The FedCausalCompose framework shows that interventional error decreases with intervention...
An audit shows that LLM agents concentrate retrieval on a small core and leave rare states in a long tail, where prediction errors build up. The CTWM controller allocates prompt budget with a single exponent and reduces tokens by 24.48% on LongMemEva...
A benchmark on 824 multi-hop questions from FRAMES compares 18 RAG pipelines with an agent loop. The best pipeline reaches 78.9%, the agent 92.7%. The most awkward result concerns reranking: a small model drops accuracy by 9 points, a large one barel...
A runtime executes LLM agent tool calls out of trajectory order but commits only after validation. Speedups up to 1.35x on benchmarks with slow tools, zero false accepts across 4,010 records. A structural shift for self-hosted deployments focused on ...
AREX-2 explores self-improvement in LLM agents through reflection and long-horizon iterations. Trained on synthetic trajectories from machine learning and algorithmic programming tasks, built on Qwen3.8-27B, it achieves 81.8 on MLE-bench Lite and 70....
BAAI has released AREX-2, a 27B parameter agent model compatible with Qwen3.8. Its propose-measure-reflect-revise loop uses scores, logs, and errors to refine answers. With a 262,144 token context and GGUF files, it matters for self-hosted deployment...
