The growing use of autonomous artificial intelligence agents in digital commerce creates new security concerns involving agent impersonation, unauthorized payments, compromised agents, and misuse of delegated authority. This research introduces the Autonomous Commerce Agent Guard System (ACAGS), a cybersecurity framewo...
A state-bound runtime assurance layer that separates probabilistic measurement from deterministic adjudication, binds an execution allowance to the decision-relevant basis of an approval, invalidates that allowance after relevant logged changes, and rechecks admissibility at dispatch distinguishes the continued validit...
Jayesh Bhadane, Ramachandra Yerramsetti, Rajesh Gupta et al.· 0 citations
Agent platforms are starting to improve their own agents: they read a deployed agent's execution traces, derive a change, have an automated verifier approve it, and release it with no human author. How much of this loop can safely run without a human? We propose two quantities a platform can measure. Verifier strength...
On-policy distillation (OPD) can succeed with surprisingly few training questions, motivating a view of questions as carriers of distributional knowledge transfer. How can we assess whether a newly generated question is valuable for distillation, and learn to generate better questions---without access to its correct an...
Jiashuo Sun, Hao Zhang, Xueqiang Xu et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
RiseHarness is a framework for iteratively improving agent harnesses with model weights fixed that treats a specific model as the unit of harness adaptation, studying how changes to shared interaction mechanisms can make existing capabilities more reliable across tasks.
Ru-Han Wang, Yu-Cheng Shi, Zong-Xia Li et al.· 0 citations
A failed gaming trajectory reveals that an agent needs intervention, but not necessarily how its execution harness should change. Effective harness adaptation therefore requires gathering diagnostic evidence, rather than merely proposing alternative recovery rules. We present KPHarness, a framework that adapts the exte...
Zhikang Chen, Yueqing Sun, Sen Cui et al.· 0 citations
LLM agents can improve across tasks without updating model parameters by storing experience from their own executions in external memory and reusing it to guide later decisions. A central design question is whether to retain only observed trajectories and outcomes or also the rules, summaries, and skills inferred from...
Large language model (LLM) agents are moving beyond reactive responses toward proactive assistance that anticipates user needs without explicit requests. However, existing proactive agents primarily address immediate needs, while many everyday situations involve delayed intentions that can only be acted on hours or day...
Lilin Xu, Linyang He, Kaiyuan Hou et al.· 0 citations
Probabilities of causation (PoCs) have developed steadily, from the binary measures first introduced by Pearl to the non-binary setting recently studied by Shu et al. As the theory has matured, PoCs have found applications in a growing range of areas, including personalized medicine, marketing and legal attribution. Sh...
Learned post-training quantization (PTQ) calibration fits quantizer parameters on a small calibration set, and for a text embedder the natural supervision is retrieval relevance. We ask two questions that are usually conflated: how far to calibrate, and whether to calibrate at all. Across three embedders (e5-base-v2, B...
Hyojung Han, Ryangkyung Kang, Youngeun Kim et al.· 0 citations
Mechanistic interpretability asks which language model components matter for a behavior, and activation patching answers by changing one component's activation and measuring its effect, at a cost growing with components and prompts. Attribution patching estimates these effects from one gradient pass, but its estimates...
REM (Reusable Experience Memory) is introduced, a framework that manages the memory lifecycle from inside the agent's think-act loop through three explicit decisions, demonstrating that the bottleneck in experience reuse is not retrieval fidelity but how experience is stored and governed across its lifecycle, opening a...
Xin-You Chen, Pedro Herrero-Vidal, Xiao-Han Chen et al.· 0 citations
