Search: “llm”

arXiv:2605.13044v1 Announce Type: cross Abstract: LLM-powered agents can silently delete documents, leak credentials, or transfer funds on a routine user request, not because the agent was attacked, b

arXiv:2605.12784v1 Announce Type: new Abstract: Advances in large language models (LLMs) have recently opened new and promising avenues for small-molecule drug discovery. Yet existing LLM-based approa

arXiv:2605.11442v1 Announce Type: cross Abstract: Large Language Model (LLM) agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digit

arXiv:2605.12477v1 Announce Type: cross Abstract: LLM-based agents increasingly operate in persistent environments where they must store, update, and reason over information across many sessions. Whil

arXiv:2605.12492v1 Announce Type: new Abstract: We introduce Pion, a spectrum-preserving optimizer for large language model (LLM) training based on orthogonal equivalence transformation. Unlike additi

arXiv:2605.11534v1 Announce Type: new Abstract: When an LLM-based embodied agent fails at a household task, the culprit could be misidentified objects, forgotten sub-goals, or poor action sequencing -

arXiv:2605.06375v1 Announce Type: cross Abstract: Large language model (LLM) alignment via reinforcement learning from human preferences (RLHF) suffers from unstable policy updates, ambiguous gradient

arXiv:2605.10380v1 Announce Type: new Abstract: LLM-based agents deliver state-of-the-art performance across tasks but incur high end-to-end latency on edge devices. We introduce Agent-X, a software-o

arXiv:2605.08715v1 Announce Type: cross Abstract: LLM-based multi-agent systems are increasingly deployed on long-horizon tasks, but a single decisive error is often accepted by downstream agents and

arXiv:2605.08761v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly expected to operate in enterprise environments, where work is distributed across specialized roles,

arXiv:2605.09584v1 Announce Type: cross Abstract: Inpatient clinical reasoning is a sequential decision under partial observability: the clinician sees the admission so far and must choose the next ac

arXiv:2602.02350v2 Announce Type: replace Abstract: Multi-Agent Discussion (MAD) has garnered increasing attention very recently, where multiple LLM instances collaboratively solve problems via struct

arXiv:2605.10488v1 Announce Type: cross Abstract: Agent-compiled knowledge bases provide persistent external knowledge for large language model (LLM) agents in open-ended, knowledge-intensive downstre

arXiv:2605.09959v1 Announce Type: cross Abstract: Self-evolving LLMs excel in verifiable domains but struggle in open-ended tasks, where reliance on proxy LLM judges introduces capability bottlenecks

arXiv:2605.09942v1 Announce Type: new Abstract: Memory retrieval in agentic large language model (LLM) systems is often treated as a static lookup problem, relying on flat vector search or fixed binar

arXiv:2510.17671v2 Announce Type: replace-cross Abstract: Many real-world optimization problems are guided by complex, subjective preferences that are difficult to express as explicit closed-form obje

arXiv:2510.22170v2 Announce Type: replace Abstract: Persona conditioning is widely used to steer large language model (LLM) behavior, but it is unclear whether it induces stable behavioral structure o

arXiv:2605.08221v1 Announce Type: cross Abstract: This paper presents NoisyCoconut, a novel inference-time method that enhances large language model (LLM) reliability by manipulating internal represen

arXiv:2605.08646v1 Announce Type: cross Abstract: Large language model (LLM) agents face a structural tension: cloud agents provide strong reasoning but expose user data, while on-device agents preser

arXiv:2605.09228v1 Announce Type: cross Abstract: Most LLM benchmarks score how well a model responds to explicit requests. They leave unmeasured a different conversational ability: noticing and actin

arXiv:2605.10327v1 Announce Type: cross Abstract: In this paper, we present SCALAR (Symbolic Conjecture and LLM-Assisted Reasoning), a neurosymbolic framework for automated conjecture generation in qu

arXiv:2602.00986v2 Announce Type: replace Abstract: Recent studies show that LLM hidden states encode reward-related information, such as answer correctness and model confidence. However, existing app

arXiv:2605.10674v1 Announce Type: cross Abstract: Rejection Fine-Tuning (RFT) is a standard method for training LLM agents, where unsuccessful trajectories are discarded from the training set. In the

arXiv:2605.10634v1 Announce Type: new Abstract: LLM-based automatic heuristic design has shown promise for generating executable heuristics for combinatorial optimization, but existing methods mainly

arXiv:2605.08964v1 Announce Type: new Abstract: In this thesis, we develop algorithms with theoretical guarantees for ensuring reliability and accountability of Machine Learning (ML) systems. As ML sy

arXiv:2605.06607v2 Announce Type: replace-cross Abstract: Recent LLM-based agents have closed substantial portions of the scientific discovery loop in software-only machine-learning research, in chemi

arXiv:2605.06936v1 Announce Type: cross Abstract: LLM-based agents are increasingly applied to the 'last mile' of Electronic Design Automation (EDA): repairing residual sign-off Design Rule Check (DRC

arXiv:2605.08057v1 Announce Type: cross Abstract: While recent advancements in inference-time learning have improved LLM reasoning on Text-to-SQL tasks, current solutions still struggle to perform wel

arXiv:2605.07699v1 Announce Type: cross Abstract: LLM-based agents are increasingly deployed for routine but consequential tasks in real-world domains, where their behavior is governed by inherently a

arXiv:2605.08061v1 Announce Type: new Abstract: We argue that decomposing reward into weighted, verifiable criteria and using an LLM judge to score them provides a partial-credit optimization signal:

arXiv:2508.10016v3 Announce Type: replace Abstract: Building interactive omni-modal assistants often relies on end-to-end multimodal alignment to fuse heterogeneous modalities, which incurs substantia

arXiv:2410.21438v3 Announce Type: replace Abstract: By pretraining on trillions of tokens, an LLM gains the capability of text generation. However, to enhance its utility and reduce potential harm, SF

arXiv:2505.24187v2 Announce Type: replace Abstract: The prevailing assumption of an exponential decay in large language model (LLM) reliability with sequence length, predicated on independent per-toke

arXiv:2605.04085v1 Announce Type: cross Abstract: Objectives: Large language models (LLMs) are increasingly used for clinical text summarization, yet structured methods to assess associated patient sa

arXiv:2605.04135v1 Announce Type: cross Abstract: Readers of applied-domain LLM capability evaluations want to know what AI systems can currently do. That literature answers a related, but consequenti

arXiv:2602.04129v2 Announce Type: replace Abstract: Heterogeneous multi-robot systems are increasingly used in long-horizon missions requiring coordinated planning across diverse capabilities. However

arXiv:2605.03804v1 Announce Type: new Abstract: Long-term personalized memory for LLM agents is challenging on resource-limited edge devices due to high storage costs and multimodal complexity. To add

arXiv:2605.03213v1 Announce Type: cross Abstract: Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocol

arXiv:2605.01078v1 Announce Type: cross Abstract: Retrieval-augmented generation and tool-integrated LLM agents increasingly depend on external textual sources. This reliance broadens the available at

arXiv:2605.03808v1 Announce Type: cross Abstract: Agentic data science (ADS) systems are rapidly improving their capability to autonomously analyze, fit, and interpret data, potentially moving towards

arXiv:2605.01740v1 Announce Type: cross Abstract: An agentic-AI runtime issues tool calls, sends messages, and actuates devices on behalf of an LLM. Catching the four ways an action can diverge from i

arXiv:2603.00822v2 Announce Type: replace-cross Abstract: As Large Language Model (LLM) agents increasingly execute complex, autonomous software engineering tasks, developers rely on natural language

arXiv:2605.03129v1 Announce Type: cross Abstract: Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style persona

arXiv:2605.01048v1 Announce Type: new Abstract: Counterfactual prompting (i.e., perturbing a single factor and measuring output change) is widely used to evaluate things like LLM bias and CoT faithful

arXiv:2605.00782v1 Announce Type: cross Abstract: Reliable spatial analysis in GIScience requires preserving coordinate semantics, topology, units, and geographic plausibility. Current LLM-based GIS s

arXiv:2602.13933v2 Announce Type: replace Abstract: Large language model (LLM) agents demonstrate strong performance in short-text contexts but often underperform in extended dialogues due to ineffici