Knowledge catalogue
arXiv:2608.06701v1 Announce Type: cross Abstract: Fixing GitHub issues in large-scale projects is a long-horizon task, especially when a fix requires changes across multiple locations or the issue des
arXiv:2608.06975v1 Announce Type: cross Abstract: Long-horizon role-playing demands that characters remain recognizable as they evolve with the narrative. Yet existing work falls short on two fronts:
I have a classic test for local LLM's. I asked for 8 ball pool game with only one HTML file and Muse Glimmer spend 21k Token(I m using full context so 128k) and only created a 220 lines of HTML and sa
Really important point and nicely explained! Two further points worth noting: (1) if an AI system relies on a harness (which as Gary notes in other writing is increasingly improtant in top models), th
arXiv:2608.07418v1 Announce Type: new Abstract: In medical education, physicians convert academic knowledge into clinical expertise through residency: years of training across thousands of encounters,
Very cool idea to have agents design complex systems by searching over the model structure itself. New research from Sakana AI introduces CEDAR, which uses LLM agents to write, simulate, and refine sy
Francesco @francedot reported that the first fully offline computer‑based LLM experience was achieved by running Muse Glimmer 30B (from @AIatMeta) locally on macOS, using Cua Driver to control native
Hey everyone ! Quick share from the cyber + local LLM side of things that I found interesting. During this week’s hacker summer camp, an AI researcher and reverse malware engineer veteran 'lordx64' on
GitHub Models is now retired I missed this news until today, when the GitHub Actions run for my simonw/research repository failed with this error message: GitHub Models is temporarily unavailable as p
Hey everyone, I constantly see high praise for M3 and M4 Macs for local LLM inference, even the base/16GB models. However, my experience has been quite different, and I'm trying to figure out if I hav
In a recent Twitter exchange, Luca Ambrogioni stated that large‑language models (LLMs) likely possess fundamental limitations that may be obscured by progress in reasoning and agentic pipelines, thoug
Disclaimer - no LLM was used to write this post/note As larger post about my setup will come later, want to give heads-up to folks who use VLLM and >= 2 GPUs. So I have pretty meaty server (8 channel
Not the biggest or shiniest, but it's mine From gaming machine inference on the original llama models, to a 4x RTX 6000 Pro Max Q + 4x 3090s local AI cluster. Pictures are in reverse chronological ord
arXiv:2512.22256v2 Announce Type: replace-cross Abstract: Software issue resolution aims to address real-world issues in software repositories based on natural language descriptions provided by users,
arXiv:2509.26331v2 Announce Type: replace Abstract: The rapid advancement of LLMs sparked significant interest in their potential to augment or automate managerial functions. One of the most recent tr
arXiv:2608.05499v1 Announce Type: cross Abstract: Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices. P
arXiv:2608.05906v1 Announce Type: new Abstract: LLM agents that repair failures often discard successful corrections, forcing later episodes to rediscover similar solutions. We study whether finalized
arXiv:2608.00641v2 Announce Type: replace Abstract: Bayesian optimization (BO) relies on a surrogate model and an acquisition function, yet the most suitable choices vary across tasks and optimization
arXiv:2608.06153v1 Announce Type: cross Abstract: Automated skill evolution enables Large Language Model (LLM) agents to continuously improve without expensive retraining. However, existing approaches
arXiv:2608.05246v1 Announce Type: new Abstract: Existing personalized LLM benchmarks primarily rely on textual personas or isolated behavioral signals, providing limited evaluation of cross-domain beh
arXiv:2608.05802v1 Announce Type: new Abstract: On-Policy Distillation (OPD) is emerging as a promising alternative to reinforcement learning for LLM post-training, yet its effectiveness in multilingu
arXiv:2606.14695v2 Announce Type: replace-cross Abstract: Language Models (LMs) have shown remarkable potential as role-playing chatbots, delivering consistent, stylized interactions when given a spec
arXiv:2608.05245v1 Announce Type: new Abstract: Reusable skills, which encapsulate the procedural knowledge required to solve real-world professional tasks, offer LLM-based agents a path toward self-e
arXiv:2608.06366v1 Announce Type: new Abstract: Electronic health record (EHR) feature engineering is a major bottleneck in clinical research and AI, accounting for 39-45% of data scientists' workload
arXiv:2608.06346v1 Announce Type: new Abstract: LLM-based agentic systems have shown remarkable capabilities in complex domains, while suffering from cascading errors and difficulty in debugging. Crit
arXiv:2608.05228v1 Announce Type: new Abstract: The 'decompose-then-verify' paradigm for LLM factuality evaluation faces a fundamental trade-off: atomic facts, i.e., one sentence conveying one unit of
Modern enterprises possess a vast amount of unstructured data, yet they frequently encounter significant challenges in managing and extracting value from it. Historically, unlocking the insights hidde
arXiv:2608.06202v1 Announce Type: cross Abstract: Large language model (LLM) benchmark evaluations are routinely used to support claims about model safety, reliability, and deployment readiness. Yet m
For a long time now, the most popular posts on LocalLLaMA have been either about using LLM in the cloud or about politics. I suspect that people using local models are about 10% now. You can say that
arXiv:2608.04565v1 Announce Type: cross Abstract: LLM-based search agents are widely used for information-seeking tasks, but their reliance on external tool returns introduces a critical security risk
arXiv:2608.04336v1 Announce Type: cross Abstract: Code generation systems make each LLM call with a model, a prompt, and decoding settings. However, existing optimization methods usually tune only par
arXiv:2608.04968v1 Announce Type: new Abstract: The capabilities of an LLM agent depend not only on its model but on the harness: the executable program that constructs context, invokes tools, verifie
I think of it like this: If you are building a simple agent with custom tools in your app -> langchain create agent If you are simply doing some LLM analysis or synthetic data creation -> langchain in
arXiv:2503.10367v2 Announce Type: replace-cross Abstract: Edge devices host domain-specific small language models (SLMs) with limited resources, while private clouds offer larger LLMs. We propose G-Bo
arXiv:2608.05013v1 Announce Type: cross Abstract: LLM agents are increasingly applied to open-ended everyday requests that span work, study, and life. These tasks are long-horizon, cross-environment,
arXiv:2608.03487v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG), which augments large language model (LLM) generation with information retrieved from databases, has become a wid
arXiv:2601.05451v2 Announce Type: replace-cross Abstract: Recent advances in text-to-SQL have been driven by larger models, better datasets, and new training methods like RLVR. However, progress remai
arXiv:2608.04074v1 Announce Type: cross Abstract: Long-context LLM decoding reads the key-value (KV) cache at every step. Loading it takes longer than computing attention over it, so throughput is ban
arXiv:2608.03223v1 Announce Type: cross Abstract: Agentic reinforcement learning enables LLM agents to learn through interaction, but sparse trajectory-level rewards reveal success without identifying
arXiv:2608.02901v1 Announce Type: cross Abstract: The key-value (KV) cache is the primary memory bottleneck in long-context LLM inference. Existing approaches attack it from opposite ends: eviction me
There are a lot of LLM benchmarks but few, if any, harness benchmarks. I am thinking this would be a really good community project to build one. End goal: a leaderboard of harness performance (multipl
arXiv:2608.02703v1 Announce Type: new Abstract: Weight-only quantization substantially reduces the storage of large language model (LLM) transformer blocks, but practical backends often retain the fin
arXiv:2608.03800v1 Announce Type: cross Abstract: An LLM-based agent is a loop that reads itself. Agentic frameworks externalize identity, memory, and disposition into editable files. The agent loads
arXiv:2608.03340v1 Announce Type: new Abstract: Predicting LLM's capabilities on real-world tasks is essential, yet the extent to which performance on commonsense benchmarks predicts downstream perfor
arXiv:2608.03609v1 Announce Type: new Abstract: Agentic systems driven by large language models (LLMs) are increasingly deployed in real-world workflows where they act on persistent operational data.
arXiv:2608.02879v1 Announce Type: new Abstract: The widespread adoption of proprietary Large Language Models (LLMs) accessed strictly through closed APIs has created a critical challenge for responsib
arXiv:2608.02604v1 Announce Type: new Abstract: LLM-based agents are increasingly being deployed for data-related tasks, including data sense-making, exploration, and retrieval. However, their perform
arXiv:2608.02996v1 Announce Type: new Abstract: Latin America is missing a foundational layer for native AI development: the benchmark layer. The benchmark layer does two things no other layer can - i
arXiv:2608.02615v1 Announce Type: cross Abstract: Cancer diagnosis and characterization require integrating complementary evidence from radiology, pathology, genomics, and clinical metadata. However,
arXiv:2602.13769v3 Announce Type: replace Abstract: Automating heuristic design in complex, experiment-driven domains requires more than iterative mutation of solution algorithms. Current LLM-based ev
arXiv:2608.02617v1 Announce Type: cross Abstract: We evaluate whether clinician pairwise preferences provide a reliable signal of clinical safety in large language model (LLM) evaluation using expert
arXiv:2608.02683v1 Announce Type: cross Abstract: Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish compl
arXiv:2608.03468v1 Announce Type: new Abstract: Historical tool-use trajectories provide valuable experience for large language model (LLM) agents to plan and coordinate tool usage. Existing approache
arXiv:2608.00009v1 Announce Type: new Abstract: Long-term memory remains a critical bottleneck for conversational AI agents, whose finite context windows cannot support coherent recall across thousand
arXiv:2608.01651v1 Announce Type: cross Abstract: Hybrid-attention large language models combine full attention with recurrent linear attention to reduce long-context inference costs, yet their autore
arXiv:2608.02046v1 Announce Type: new Abstract: LLM companions are deployed at scale in personally consequential settings, yet poorly evaluated. Existing benchmarks use hand-authored scenarios and pro
arXiv:2608.01046v1 Announce Type: new Abstract: The rapid spread of large language models (LLMs) across the web raises concerns about misinformation, academic integrity, automated content manipulation
arXiv:2510.01925v3 Announce Type: replace Abstract: Reward models (RMs) play a critical role in enhancing the reasoning performance of LLMs. For example, they can provide training signals to finetune
arXiv:2608.02123v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference only when drafted continuations survive target-model verification. Semi-autoregressive drafters such as D
152 generations, deterministic grading (exact number/string/JSON/regex), no LLM judge on my 16GB laptop. task type | deepseek-r1:1.5b (1.1GB) | llama3.2:3b (2.0GB) | gemma:2b | codellama 7b arithmetic