It is common to train Large Language Models (LLMs) for agentic tasks with Reinforcement Learning (RL) from scalar rewards. However, this throws away the fine-grained information about the environment that the agent experienced during the trial (e.g., error logs). To utilize this …
⏱ Độ trễ thật của tab này: trung bình 7.2 giờ sau khi CVE được công bố (n = 5385, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
Autonomous agents modify prompts, memories, tools, workflows, and policies using interaction histories. Yet a plausible modification is not necessarily suitable for persistent adoption: candidate selection is adaptive, evaluators may be imperfect, and local gains can hide degrada…
arXiv:2611.17696v1 Announce Type: new Abstract: Long-horizon business workflows fail in two ways: errors accumulate as a chain of activities lengthens, and the knowledge an activity needs is written in a different vocabulary from the user's request. We study whether such workflo…
arXiv:2611.10723v1 Announce Type: new Abstract: Security fixes usually reach users as compiled updates, but deployment delays leave unpatched systems exposed. During this window, comparing patched and unpatched binaries can reveal how to exploit a vulnerability, turning a defens…
arXiv:2611.15276v1 Announce Type: new Abstract: Agent self-improvement requires feedback about task success, yet external feedback may be unavailable at test time. Agents must then infer success from observable evidence, and incomplete verification can misguide subsequent update…
arXiv:2611.17340v1 Announce Type: new Abstract: Large language models are expensive to update through full retraining. Parameter-efficient fine-tuning reduces the cost of adaptation, but repeated adaptation creates a growing pool of task-specific LoRA adapters. This pool complic…
arXiv:2611.17806v1 Announce Type: new Abstract: Long-horizon agents increasingly serve as persistent personal assistants across modern web platforms, managing schedules, applications, and multi-step plans over weeks or months. Users often return to an ongoing conversation after …
arXiv:2611.17577v1 Announce Type: cross Abstract: Distributed coordination of electric vehicle (EV) charging with the alternating direction method of multipliers (ADMM) keeps EV constraints private but assumes that every participant follows the algorithm. This assumption fails i…
Recent work shows that multimodal agents increasingly self-improve without recurring human annotation. However, each self-improvement mechanism is designed and evaluated within a single scenario, leaving its preconditions unverified under cross-scenario transfer. This survey inve…
arXiv:2611.15178v1 Announce Type: new Abstract: Reinforcement learning sharpens LLM reasoning, but parameter updates are expensive, forgetful, and opaque; training-free libraries swap gradients for a textual store but still use trajectory-level, correlation-based admission and f…
arXiv:2611.16048v1 Announce Type: new Abstract: Personalized LLM services place private facts and application instructions into a prompt, then retain representations of that context for later inference. Latent-state LLMs compress part of this history into fixed-size recurrent st…
arXiv:2611.10165v1 Announce Type: new Abstract: Existing LLM post-training quantization techniques determine precision before inference begins, yet the precision a model requires varies dynamically across prompts, layers, and inference phases. We present AutoEMatic, a full-stack…
arXiv:2611.14910v1 Announce Type: new Abstract: Large language models (LLMs) require frequent knowledge updates across heterogeneous domains, but existing editing methods fail when applied sequentially to multi-task settings. We trace this collapse to inter-domain null-space mis…
arXiv:2611.15215v1 Announce Type: new Abstract: In robotics and embodied AI, a core challenge for world models is adapting to sudden, persistent, yet initially unknown changes in robot dynamics during interaction. For instance, when a robotic arm grasps an object with an unknown…
arXiv:2611.14698v1 Announce Type: new Abstract: Incrementally verifiable computation (IVC) allows a prover to maintain a short proof that can be efficiently updated after each computation step, without retaining or recomputing the preceding execution. Standard IVC schemes do not…
arXiv:2611.16151v1 Announce Type: new Abstract: Hardware fault injection attacks threaten machine learning systems, yet their impact on reinforcement learning (RL) has received little attention despite the use of RL in safety-critical applications. This paper presents a security…
arXiv:2611.16495v1 Announce Type: new Abstract: We implement privacy-preserving local electricity exchanges using an automated market maker on the Hyperledger Besu network under QBFT consensus. The proposed protocol operator collects individual electricity positions off-chain an…
Distribution matching distillation (DMD) has emerged as a leading paradigm for distilling diffusion models into few-step students, where an auxiliary fake score model tracks the student's distribution and the discrepancy between the teacher and fake predictions drives the student…
arXiv:2611.13232v1 Announce Type: new Abstract: We present W-ISA, a software instruction set and transactional runtime for executing weight-space intervention programs on pretrained language models. Shape-checked instructions express parameter updates, projections, ablations, an…
arXiv:2611.13491v1 Announce Type: new Abstract: Detecting backdoor attacks in federated learning (FL) is challenging because malicious clients can manipulate the global model while preserving main-task performance. Static model-update statistics may therefore fail to clearly dis…
arXiv:2611.10279v1 Announce Type: new Abstract: Safety-aligned language models are known to suffer degradation in refusal behavior following domain-specific fine-tuning, even when the fine-tuning data is entirely benign. The predominant mitigation strategy, preference optimizati…
arXiv:2611.10056v1 Announce Type: new Abstract: Open-weight LLMs are routinely fine-tuned from public repositories, yet task-specific adaptation can silently erode safety alignment inherited from instruct-tuned bases. This is a supply-chain risk when organizations ship third-par…
arXiv:2611.10099v1 Announce Type: new Abstract: We study a safety harness that improves itself without touching model weights. Enmo Safety wraps a chat model with a deterministic input assessment, trigger-matched safety guidance, spotlighting of untrusted content, and an output …
We present FAME-QP, a GPU-accelerated solver for dense quadratic programs arising in linear model predictive control. FAME-QP combines constraint-dependent operator representations with fused single- and two-kernel iterations replayed through CUDA graphs, automatically selecting …
RLVR trains language models to reason by rewarding correct final answers. A widely used algorithm, group-relative policy optimization (GRPO), gives every token of a solution the same credit, so dense process rewards have been proposed to credit intermediate steps, for example wit…