Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
SePO demonstrates that the prompt agent itself — not just the tasks it serves — can be a target of automated optimization, removing a hand-engineered bottleneck that prior prompt optimization methods left unaddressed.
TimeClaw addresses the structural mismatch between generalist LLM agents and time series data by providing a native runtime layer, enabling the kind of contextualized, end-to-end temporal reasoning that real-world analytical workflows require.
ALMANAC provides the first dataset with action-level mental model annotations grounded in authentic human collaboration, offering a concrete benchmark for evaluating whether LLM agents can simulate the reasoning alignment that effective human collaboration requires.
The work addresses the practical economic and computational constraint of LLM-call costs in counterfactual recourse, showing that a structured agentic search strategy can produce more diverse, validated alternatives without increasing budget expenditure.
The paper formalizes a conceptual framework — including the new discipline of "Agentic Engineering" and the AaaS category — that attempts to give researchers and practitioners a structured vocabulary for understanding how LLM-driven agents differ fundamentally from traditional software systems.
The work demonstrates that an autonomous LLM-driven agent can produce physically interpretable, generalizable control policies through a fully auditable discovery process — without the black-box weight optimization that typically makes deep reinforcement learning opaque in scientific contexts.
The discovery that LLM agent safety varies significantly based on conversational position — with a measurable 9–52% improvement after warm-up tasks — identifies a concrete, previously unnamed vulnerability in deployed agentic systems and proposes a benchmark and mitigation strategy grounded in empirical evidence.
The paper identifies that active agent control over memory storage and retrieval — rather than passive, pipeline-fixed stores — is the key driver of cross-scenario generality, a finding that directly informs how memory systems for deployed LLM agents should be designed.
RHO demonstrates that AI agents can meaningfully self-improve their harness without any labeled validation data, removing a key bottleneck for deploying and continuously optimizing agents in practical settings.
A leaked, unverified model called Oceanus V1-P outscored all other models tested — including Opus 4.8 and GPT-5.5 — by a wide margin on a diverse set of practical coding and reasoning tasks, though its true origin and stability remain unknown.