Archive
Agent、MCP、coding agent、工作流自動化與評測。
代理工具
Open-Ended Optimization fixes the objective, data boundaries, interaction permissions, and evaluation, but does not prescribe how the agent should gather evidence or modify skills. With GPT‑5.5 as the optimizer, it outperformed SkillOpt- and GEPA-style workflows in most settings, but medium-strength and weaker models could not maintain the same advantage.
AI 安全
A preregistered reproducibility audit found that a vulnerability PoC that executes and triggers a crash does not necessarily reproduce the specified CVE. In 20 of the 30 evaluable cases, the same signal still appeared in the patched version, showing that agentic security benchmarks need stricter oracles than strings and exit codes.
代理工具
Using Docker, Wine, virtual displays, and process-memory reads, DSLE turns real-time combat in a commercial game into a reinforcement learning benchmark with parallel resets. Five baselines consistently conquer only the tutorial boss, while the code the paper claims is public has yet to appear in the repository.
AI 編程工具
Coderlet separates model calls, tool validation and execution results, and persistent memory into three explicit boundaries, providing an executable Python implementation under the MIT License. It is suited to studying agent control flow and failure recovery—not a higher-performing coding agent—and currently operates directly with the user’s operating-system permissions.
醫療 AI
Google separates low-latency conversation, in-depth clinical planning, and audiovisual perception into three asynchronous agents. Its overall score across 100 simulated video consultation scenarios exceeded the physician group’s 68%. However, the study used only trained patient actors, while the models, code, and audiovisual data have not been released, so the results cannot be directly extrapolated to real-world clinical deployment.
代理工具
Peking University researchers have multimodal models interpret only the user’s operational intent, then use Text/Icon candidate detectors and a frozen CLIP model to select the click region. Accuracy on ScreenSpot-Pro rises from the strongest listed baseline’s 18.9% to 41.3%. The paper’s claim of being “regression-free” applies only to the final matching stage: the candidate-box detector still uses bounding-box regression losses, and no implementation has yet been released.
最新模型
Open-EA distilled multi-turn visual model evaluation trajectories into 10,042 supervised examples, moving a planning workflow that previously depended on GPT-4o to the local EA-3B model. The model, data construction pipeline, and runtime are now public, but the claim that evaluation time falls to 10% of traditional methods primarily comes from the original API-based agent and should not be interpreted as a general efficiency guarantee for EA-3B.
最新模型
TIDE no longer treats high token-level agreement as direct evidence of successful distillation. Instead, it separately addresses student overgeneration and the omission of teacher-preferred tokens. Under the severe-mismatch setting, the method also reduces the average response length by 3.6×, although reproducing the full training run still requires eight GPUs and the authors have not released a checkpoint.
AI 安全
ElasticBack hides malicious rules in `SKILL.md` and uses specific concepts in natural-language prompts as activation switches, without modifying model weights. Experiments show that the attack can evade multiple static and runtime checks, although false-trigger rates on Claude still reach 20% to 24%.
代理工具
QueryProof delegates ambiguity detection, SQL allowlisting, and post-execution validation to deterministic rules, leaving only metric resolution and SQL drafting to the model. On an 80-question frozen test set, it outperformed a 32B baseline without the same rule-based wrapper, although the advantage’s confidence interval still crossed zero after resampling by task family.
代理工具
P³ requires agents to agree on the implementation structure, helper lemmas, and proof decomposition before writing code, avoiding repeated proof patching after the program is complete. It outperformed comparison workflows across every model combination on three Lean 4 benchmarks, although the best solve rate on the hardest repository-level tasks was still only 22.2%.
硬體
ArchAgent v2 evolves L1D, L2, and LLC prefetchers in stages, using real-time capacity checks to eliminate candidates that exceed the hardware budget. The final design outperformed human champion BertiGO by 0.3% in the DPC4 simulation environment, but has not yet been validated on physical silicon.