long-horizon
Frontier agents produced three genuinely new ideas out of 252 attempts News
A systematic evaluation of seven frontier models on 36 long-horizon research tasks found that agents behave like engineering optimizers rather than researchers, with only a handful of solutions surviving manual review as genuinely novel and more of them turning out to be shortcuts aimed at the evaluator.
The Same Model Scores 52 or 81 Percent Depending on the Code Wrapped Around It News
A new agent harness lifts Qwen 3.7-Plus from 51.8% to 80.7% on a long-horizon coding benchmark without touching the model, by keeping task state outside the conversation and updating it only from facts a read-only auditor verified in the environment.
LaMem-VLA gives robots a memory so they stop forgetting the task News
A new framework called LaMem-VLA tackles the 'goldfish memory' problem in robot policies by compressing past experience into latent memory tokens and weaving them into the robot's current reasoning, targeting long-horizon manipulation tasks that single-frame models fail.
A 32B model reaches frontier level by learning what to remember News
New research reframes agent memory as a trainable skill rather than a growing transcript - and shows that optimizing memory alone lets a 32B open model rival Claude Opus, and a 4B model leap from 4% to 78% on a benchmark.