Knowledge catalogue
arXiv:2609.08592v1 Announce Type: new Abstract: Evaluating tool-augmented LLM agents requires diverse, realistic user inputs yet most evaluation frameworks use flat role descriptions ('you are an angr
arXiv:2609.05837v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed in real-world applications through tool-use APIs, yet training them for specific environments remains fundame
arXiv:2606.19795v2 Announce Type: replace-cross Abstract: Electronic design automation (EDA) is multi-stage and handoff-heavy, relying on transfers among humans, design artifacts, and multiple tools.
arXiv:2609.08861v1 Announce Type: new Abstract: Benchmark scores are a central currency in model releases: they inform purchasing decisions, shape public trust, and influence policy. Yet, a key assump
arXiv:2609.07102v1 Announce Type: cross Abstract: Astronomical spectra encode rich physical information, but drawing scientific conclusions from spectral features typically requires expert interpretat
arXiv:2609.05437v1 Announce Type: new Abstract: Previous AI alignment efforts have focused primarily on first-order social norms -- teaching models what is socially acceptable or unacceptable (e.g., `
arXiv:2609.05776v1 Announce Type: new Abstract: Evaluating enterprise agents on domain-specific benchmarks is critical, yet public benchmarks rarely evaluate whether agents can integrate business know
arXiv:2602.05354v3 Announce Type: replace Abstract: Autonomous web agents are increasingly deployed in moderation and policy enforcement, where correct decisions often depend on evidence that is not i
arXiv:2601.13591v3 Announce Type: replace Abstract: Recent LLM-based data agents aim to automate data science tasks ranging from data analysis to deep learning. However, the open-ended nature of real-
arXiv:2609.08790v1 Announce Type: cross Abstract: Threat hunting increasingly depends on converting unstructured knowledge (e.g., Cyber Threat Intelligence reports) into actionable hunt leads: concise
arXiv:2609.10155v1 Announce Type: new Abstract: We approach a cognitive simulation perspective on episodic and semantic memory in multiple-choice question answering by incorporating text from individu
arXiv:2609.08015v1 Announce Type: new Abstract: Long-running AI agents may read state, reason, wait for tools or human approval, and perform an external action much later. The state that justified the
arXiv:2503.19599v3 Announce Type: replace-cross Abstract: While software requirements are often expressed in natural language, verifying the correctness of a program against such requirements is a har
arXiv:2609.06250v1 Announce Type: cross Abstract: Security Operations Centers (SOCs) process large amounts of tickets, most of which are low-interest events not worthy of further investigation. The re
arXiv:2605.21694v2 Announce Type: replace-cross Abstract: Connecting large language models (LLMs) to defensive enforcement requires more than asking a model whether an attack is happening. A defender
arXiv:2609.07901v1 Announce Type: new Abstract: Weight quantization largely determines the economics of serving open-weight LLMs. Its costs are usually assessed with capability benchmarks, on which 4-
arXiv:2609.10505v1 Announce Type: new Abstract: Credit default prediction is a tabular classification problem in which modest gains in F1 translate directly into reduced financial exposure. We ask whe
arXiv:2609.08258v1 Announce Type: new Abstract: Long-running language-model agents depend on persistent memory. Many agent-memory systems preserve history through soft revocation: a contradicted fact
arXiv:2609.08789v1 Announce Type: cross Abstract: Frontier AI developers publish safety frameworks that commit them to evidencing whether their models are dangerous. The European Union and California
arXiv:2609.06835v1 Announce Type: cross Abstract: Agentic AI systems execute complex tasks through long-horizon workflows of planning, tool use, and multi-agent coordination. Task failures in these sy
arXiv:2609.05928v1 Announce Type: cross Abstract: Large language models now compute correct tax liabilities on over 90% of well-formed cases in statutory benchmarks, which makes them candidates for th
arXiv:2609.09561v1 Announce Type: new Abstract: Surveys remain the primary way researchers grasp the lineage of methods within an AI subfield, but they scale poorly against the current rate of publica
arXiv:2609.05910v1 Announce Type: cross Abstract: Reinforcement learning (RL) excels on tasks with verifiable rewards, but in open-ended tasks, the reliability of reward models remains a key challenge
arXiv:2609.07065v1 Announce Type: new Abstract: Agent-to-agent (A2A) alpha discovery is slowed by repeated feedback cycles between mining and evaluation agents, whose hand-offs, in contemporary LLM mu
arXiv:2504.00285v2 Announce Type: replace Abstract: Large Language Models (LLMs) are effective at deceiving when prompted to do so. Models that demonstrate better performance on reasoning tasks are al
arXiv:2609.09628v1 Announce Type: cross Abstract: Inferring speaker relationships from spoken conversations is an important step towards socially aware speech understanding. However, this task remains
arXiv:2609.05677v1 Announce Type: cross Abstract: Lifelong LLM agents increasingly rely on external skill artifacts as one element for preserving and reusing capabilities over time. These skills (usua
arXiv:2609.08826v1 Announce Type: cross Abstract: When an external reference set (an anchor) is used to decompose an LLM-judge panel's error into a quality signal and a shared common-mode error, stand
arXiv:2609.05518v1 Announce Type: new Abstract: Despite the strong capabilities of multimodal large language models (MLLMs), their parametric knowledge remains incomplete and difficult to update, moti
arXiv:2609.05905v1 Announce Type: cross Abstract: LLM agents are increasingly used for live forecasting, where they retrieve up-to-date information and produce estimates for unresolved future events.
I like this framing a lot: agent improvement is harness improvement, not model improvement The interesting interventions are often at the tool boundary: - what context you pass - when tools are provid
arXiv:2609.05992v1 Announce Type: cross Abstract: As LLM-based agents continue to advance, their evaluation has become increasingly multifaceted: a capable agent must not only achieve high task comple
arXiv:2510.10681v2 Announce Type: replace-cross Abstract: High-quality data is a cornerstone of large language model (LLM) pretraining, yet its growth has not kept pace with the needs of frontier mode
arXiv:2609.05933v1 Announce Type: new Abstract: Efficiency is increasingly important for Large Language Model (LLM)-based multi-agent systems (MAS), as larger models and more agents introduce substant
While GPUs remain essential for LLM training and inference, enterprise‑scale agentic AI workloads shift the focus to orchestration rather than raw compute. Agents must break down requests into subtask
We’ve been building PipesHub for a while now, and I’d love to get more teams to try it and tell us where it breaks. The problem we kept running into was pretty simple: Building an AI app over company
I'm testing a new approach for reducing the cost of image-based LLM inference. I evaluated it on the MOMA Graph benchmark, using 1,315 questions. Compared with using GPT-4o to process the original ima
arXiv:2609.04611v1 Announce Type: new Abstract: LLM agents are rapidly becoming production software, deployed to handle customer service, adjudicate disputes, and operate internal systems. Notably, th
arXiv:2609.04792v1 Announce Type: cross Abstract: Activation steering has shown promise for controlling LLM generation along well-defined attributes, but it remains unclear whether it can handle the m
arXiv:2609.04865v1 Announce Type: new Abstract: Skill libraries improve the sample efficiency of agentic reinforcement learning (RL) by enabling large language model (LLM) agents to reuse procedural k
arXiv:2609.04280v1 Announce Type: cross Abstract: Modern LLM-based agents operate through a harness of tools, reusable skills, and specialist agents that shapes what they observe and what they can do.
arXiv:2609.05274v1 Announce Type: new Abstract: LLM agents deployed for software engineering fail expensively: they act confidently wrong, and bad actions are recognized only after costly execution an
Our research team has been exploring an alternative approach to achieving interactivity and better responsiveness with LLM systems. One of the team members wrote up a post about it: https://research.y
arXiv:2609.05314v1 Announce Type: new Abstract: Building automation systems generate rich sensor data yet remain insight-poor because heterogeneous point naming, missing metadata, and fragmented docum
arXiv:2609.05151v1 Announce Type: cross Abstract: Leveraging their inherent sparse event-driven computation, spiking neural networks (SNNs) offer a promising path toward energy-efficient large languag
arXiv:2609.05025v1 Announce Type: cross Abstract: Hallucination-where a language model generates outputs that are factually incorrect or unsupported by the source-is a major challenge for both prompte
arXiv:2609.05395v1 Announce Type: new Abstract: Data-sovereignty regulations increasingly require public institutions to deploy open-source, on-premise LLM agents that chain multiple tool-calls across
arXiv:2609.04773v1 Announce Type: cross Abstract: Distillation is common in LLM post-training, where on-policy knowledge distillation (OPKD) uses student-generated trajectories to prepare the student
I’ve been setting up an M1 Max Mac Studio (24-core GPU, 32GB unified memory) as a local LLM server and wanted to compare MLX vs llama.cpp on Qwen3.8-27B. I tried to keep the model footprint and benchm
arXiv:2609.04489v1 Announce Type: cross Abstract: Pause-token methods improve LLM reasoning by inserting special tokens into sequences. Prior work explains these gains through computational expressivi
arXiv:2609.04486v1 Announce Type: cross Abstract: Intent-based networking realization starts by translating high-level intents into low-level network configurations. Recent approaches have shifted tow
Hi, I've been wanting to run my own local LLM for some time and I finally saved enough to get a budget GPU. I can spend 700 at most, and I'm looking for a GPU that can run quantized 30B~ parameter mod
arXiv:2609.03860v1 Announce Type: new Abstract: Retail supply chain operations rely on coupled decision modules that must adapt as requirements evolve. LLMs offer a natural-language interface for this
arXiv:2609.03734v1 Announce Type: cross Abstract: BLEU-4 is the standard metric for evaluating sign language translation (SLT), but spoken-language metrics may not adequately reflect sign language pro
arXiv:2609.03781v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in multilingual settings, yet their safety is still evaluated primarily in English. This limits our
arXiv:2606.20954v2 Announce Type: replace-cross Abstract: Long-running language-model systems accumulate interaction history that outgrows the context window, so they must continually evict. When an e
arXiv:2609.02897v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by drafting candidate tokens and verifying them in parallel. Tree-attention drafters such as EAGLE-3 are
arXiv:2609.03215v1 Announce Type: new Abstract: Writing proficiency manifests in how students develop content, organize ideas, choose words, and use language. Despite growing interest in LLM-based stu
arXiv:2609.03425v1 Announce Type: cross Abstract: Humans are the transport layer between AI systems, losing context at every hop. We present the Civilization Framework, whose addressable party is the
arXiv:2609.03718v1 Announce Type: cross Abstract: Computer-aided engineering (CAE) simulation is among the largest and most demanding areas of engineering, where setting up a solver such as OpenFOAM,