Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-07-12 · source-backed
Instead of cloning full teacher demonstrations that mismatch the contexts a student hits at test time, spend a fixed teacher-labeling budget on short continuation rollouts that branch from the student's own trajectories (arXiv). On HotpotQA, ALFWorld, and Terminal-Bench-Dev, bounded teacher continuations beat behavioral cloning at matched budgets. If you're fine-tuning an agent, generate a few teacher-corrected continuations from your student's failure states rather than paying for many complete expert trajectories.
Each link below shares sources, entities, or timing with this story.
"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...
SkillForge (arXiv 2608.24747) notes that skill-extraction approaches like SkillRL never verify whether a stored skill still works against the current environment, so the bank grows monotonically while quality rots. It makes skill usage explicit during interaction so RL optimiz...
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...
The method turns tool use from a hardcoded prompt into a learned runtime behavior, then applies cost-aware RL teaching the agent when reading external state is worth the token budget. Qwen3-8B reaches a 96.9% average success rate against SkillOS at 80.2% and SkillRL at 89.9%,...
SkillPyramid extends Voyager-style libraries with a hierarchical topology plus a self-evolution loop, raising average reward 38% and cutting execution steps 27.7% across ALFWorld, WebShop, and ScienceWorld. The takeaway: don't append every successful trajectory as a new flat s...
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...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.