CORTEXA
← Browse
arxivcs.AI2026-07-18

AgentBrew: Lifelong Knowledge Brewing from Strong Teachers to Weak LLM Agents

Yangqin Jiang, Chao Huang

Deploying LLM agents typically requires a compact test-time student, even if a stronger teacher is available during training. We study knowledge brewing: distilling a teacher's interactive experience into a persistent external memory for the student. Crucially, this requires no weight updates, expert demonstrations, ground-truth labels, or test-time teacher access. This setting poses two challenges: environments provide only sparse, binary feedback, and teacher-authored notes must be inherently tailored to be concretely executable by a substantially weaker student. To address these hurdles, we propose AgentBrew, comprising two coupled components. First, a failure-triggered teacher--Ralph Loop mitigates sparse feedback by transforming student failures into environment-validated notes. Second, student-aware synthesis calibrates teacher knowledge to the weak executor's operational granularity, yielding model-specific, actionable guidance. Extensive evaluations and comprehensive ablations across coding, math, and tool-use tasks demonstrate that this asymmetric, training-free brewing paradigm produces highly capable yet deployable LLM agents.

View free PDFSource page

Related papers

arxiveess.SYcs.AIcs.MA2026-06-30

A Tutorial on Autonomous Fault-Tolerant Control Using Knowledge-Grounded LLM Agents

Javal Vyas, Milapji Singh Gill, Artan Markaj, Felix Gehlhoff, Mehmet Mercangöz

Fault recovery in process plants still relies heavily on plant operators, especially when faults fall outside predefined supervisory logic. Operators interpret alarms, procedures, P\&IDs, interlocks, and process trends, then decide how to move the plant to a safe operating mode w…

View free PDFSource page
arxivcs.CRcs.AI2026-06-26

LLM agents security duality: a comprehensive survey of self-security and empowered cybersecurity

Yiwei Xu, Yong Zhuang, Xuanming Liu, Tian Zhang, Bowen Xiao, Xiaoyang Xu, et al.

Large language model (LLM) agents are rapidly being integrated into real-world systems. Their autonomy and tool-use capabilities generate substantial value while simultaneously expanding the security attack surface. This survey provides a comprehensive overview of the opportuniti…

View free PDFSource page
arxivcs.CRcs.AIcs.LG2026-07-20

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security

Devina Jain, David Hartmann, Chuan Li

LLM-based agents process external content, exposing them to prompt injection and multi-turn manipulation. Most safety benchmarks evaluate defenders against fixed attack pools collected before evaluation, single-turn or multi-turn. We present a 21-scenario benchmark for \emph{adap…

View free PDFSource page
arxivcs.AIcs.CL2026-07-07

PolyWorkBench: Benchmarking Multilingual Long-Horizon LLM Agents

Hongliang Li, Yijin Liu, Zhiwei Zhang, Zihe Liu, Xinyue Lou, Jinan Xu, et al.

Large language model (LLM) agents have shown strong performance in long-horizon tasks that require planning, tool use, and interaction with external environments. However, most existing benchmarks implicitly assume a monolingual setting, where the entire execution process, includ…

View free PDFSource page
arxivcs.LGcs.AI2026-07-03

No Time Like the Present: Agentic Test-Time Training for LLM Agents

Yanbo Wang, Jinhua Hao, Yuze Shi, Kun Yuan, Ming Sun

LLM agents often degrade over long episodes: as trajectories grow, they revisit explored states, repeat failed actions, and lose strategies that previously worked. Test-time training (TTT) offers a way to adapt model weights to the evolving task state, but existing LLM TTT method…

View free PDFSource page
arxivcs.AIcs.CL2026-06-28

PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents

Seongjae Kang, Taehyung Yu, Sung Ju Hwang

LLM agents handle user requests on behalf of organizations through tool calls and must follow the company policies stated in their system prompts. Prior work approaches this as a safeguarding problem -- external checks that block non-compliant agent actions. We argue that policy…

View free PDFSource page