Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-03-11 · source-backed
First academic paper providing a replicable blueprint for building terminal-first AI coding assistants. Dual-agent planning/execution separation, workload-specialized model routing (5 workflow slots), adaptive context compaction, cross-session memory. Install via uv pip install opendev. arXiv
Each link below shares sources, entities, or timing with this story.
Here's the number that should sit in every "agents will replace engineers" thread: 15.2%. That's the best model. The mean across 15 frontier models is 4.3%. Tencent Hunyuan's Long-Horizon-Terminal-Bench put 15 frontier models against 46 long-horizon terminal tasks across nine...
Same weights. Same tasks. Same time budget. One change to the harness, and fail-to-pass on SWE-bench Verified went from 28% to 49%. The setup in arXiv 2608.26218 is clean enough to be worth describing precisely. 169 SWE-bench Verified tasks, a 20,480-token context window, a fi...
Tsinghua's CompactionRL folds summarization into RL rollout collection so the agent learns what to keep when it compresses, optimizing summary and task under one reward. Under fixed 64k–80k windows it adds +5.5 to +7.0 on SWE-bench Verified and +3 to +6.8 on Terminal-Bench ver...
arXiv 2608.08311 describes an agent that continuously rewrites its own tools, prompts, context assembly, and core implementation through reviewed commits. On Opus 5: 86.74% Terminal-Bench 2.1, 90.69% OSWorld-Verified, 0.2301 normalized reward on CL-Bench. It also documents "Ho...
"Remember When It Matters" (arXiv:2607.08716) attacks behavioral state decay, where task-critical instructions get buried or evicted on long runs, using a second memory agent that proactively injects reminders into the action agent's context. It gained +8.3pp pass@1 on Termina...
The diagnosis in this paper is better than the fix, and the fix is very good. Recurrent memory agents fail at long context, but not for the reason most people assume. The bottleneck isn't capture. It's retention. Retention falls below 30% at 896K tokens because every consolida...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.