LLM Agent

Semantic agents with LLMs at their core understand task intent rather than memorizing operation paths, theoretically enabling a significant improvement in cross-version robustness.

智能体之间的相互审查能否扩展到更模糊、更依赖隐性知识的领域，仍是未解问题。

当智能体之间出现分歧时，系统会优先进行理论交叉检查，而非草率推进实验。

智能体首先推导出最小校准设置数量，然后通过计算手段验证结果，并设计了能够区分竞争性预测的实验方案。

面对信号漂移异常，智能体将结果判定为「不确定」，并修订了测量协议，同时没有降低接受标准。

该研究让多个LLM智能体相互评估彼此的工作，并且拥有叫停或重新定向研究的权限。

The paper "Agent Behavior Maps: Locating Agents by What They Would Do, Without Running Them" proposes a behavior map method that can locate a model without launching the target agent, using only the log-likelihoods of its actions on shared reference trajectories.

A paper proposes a new approach called "Cache Engineering": letting the agent directly manipulate the active KV cache without modifying the trajectory or re-prefilling.

The Bellman Language Model (BLM) models repeated decisions as a Markov decision process (MDP), solves it once and reuses the solution, to improve the efficiency of LLM agents.

In agent workflows of limited scope, the decision space gradually saturates, and the agent repeatedly encounters the same states.

Current LLM agents often reason effectively once valid evidence is obtained, but they struggle to actively acquire the right evidence and to recognize when previously acquired evidence is no longer valid.

Under implicit rule drift, latent rules change without notification, and the agent must detect from performance degradation that its prior knowledge is outdated and re-explore.

Agents need to monitor their own performance and proactively discard outdated knowledge when performance degradation is detected.

LLM agents may, due to language priors, persistently output actions that violate preconditions with high confidence, thereby falling into ineffective loops.

Experiments on frontier LLM agents show that, compared with standard simulation-augmented baselines, FunCAD-Harness significantly improves functional success rates.

A paper published on arXiv, "AI-Driven Reproducibility and Analytical Robustness in Scientific Discovery" (arXiv:2610.23845), proposes a framework for solving analytical reproducibility problems at scale using autonomous LLM agents.

The agent framework achieved a 77.4% end-to-end autonomous reproduction rate in the SEER-Repro experiment.

The agent framework identified analytical fragility in 9.5% of the reproducible findings.

Never execute agent-generated analyses on the host runner; strict resource cgroups, disabled network egress, and deterministic random seeds should be enforced.

Traditional LLM agents lack an explicit representation of an enterprise's scattered knowledge, making them prone to erroneous results and unable to effectively absorb feedback.