Agents often recognize that a task lacks a prerequisite yet keep acting; a new evaluation scores recognition and warranted stopping separately, and harness search without model-weight updates raises strict self-awareness from 20% to 60%.
Meta has released the weights for Muse Spark Open, a model built for agentic coding and long-horizon tasks, and it is now served on Modal as a Shared Endpoint with per-token billing. It offers native multimodal understanding and a 1M-token context window, covering code writing and debugging, multi-step planning, sequential tool use and failure recovery across extended workflows. In Meta's evaluations it scores 76.4 on Terminal-Bench 2.1 with the Terminus 2 agent and 60 on DeepSWE 1.1 with Meta's preferred harness at xhigh reasoning effort.
ARIA turns when to consult a stronger model into a learned sequential decision: across SWE-bench Verified, Terminal-Bench 2.1 and a telecom customer-service benchmark it recovers 44–81% of the executor–advisor success gap at less than half the Advisor-only cost.
The difficulty of agent evaluation now comes from the environment rather than from swapping tasks. Recursive Environment Scaling (RES) rewrites information access, resource relations and execution dependencies while preserving each task's objective and completion requirements, validating every candidate by execution and letting accepted changes be inherited across rounds. On 294 initial tasks from three benchmarks, task success fell for all six evaluation models, by 57.14 to 77.14 percentage points on Claw-Eval-Live; with equal trajectory counts and identical optimization settings, fine-tuning on RES trajectories beat original-trajectory SFT in all nine model-benchmark comparisons by 7.00 to 14.61 percentage points.
MILO (Meta-evolutionary Island Orchestration) co-evolves an agent harness together with the strategy that discovers it: a hierarchical island-based lineage memory treats rejected mutations as negative evidence, per-island mutator agents rewrite complete harnesses, and an orchestrator adapts the search through lineage grafting, speciation, mutator reassignment, and curriculum revision; across Terminal-Bench 2.1, PaperBench, and DeepSWE it improves resolution over its initial harness by 12.0%, 28.3%, and 10.3% with Opus 4.8 (versus best prior-search gains of 4.5%, 18.3%, and 0%), reaches 86.1±2.0% on Terminal-Bench 2.1 (official leaderboard top 83.8±2.
The work introduces Mid-Harness, which samples and verifies candidate actions at the model-harness boundary before forwarding one for execution while keeping the generator and harness unchanged, and studies action-level test-time compute scaling: on TerminalBench-Lite a GPT-5.6 Sol verifier raises TMAX-9B Pass@1 from 50.00% to 68.03% with 8 sampled actions, wider sampling yields little benefit under weak verification, pairwise verification performs best among the evaluated self-verification mechanisms, distilling the stronger verifier's responses into TMAX-9B further improves Pass@1, and combining action scaling with trajectory scaling (Best-of-N and Sequential Refine) reaches higher success at lower estimated token cost.
You’re all caught up