Knowledge catalogue
arXiv:2606.02418v1 Announce Type: cross Abstract: Quantum LDPC code discovery requires searching large algebraic design spaces while reliably certifying the parameters and equivalence classes of any c
arXiv:2511.21140v4 Announce Type: replace-cross Abstract: Large language models (LLMs) are widely used as scalable evaluators of model responses in lieu of human annotators. However, imperfect sensiti
Research demonstrates that LLM-based agents can generate functionally correct patches that pass all tests while still containing security vulnerabilities, challenging the assumption that test-passing
arXiv:2606.01490v1 Announce Type: cross Abstract: We present a controlled experiment evaluating 12 multi-agent LLM collaboration topologies for software architecture design. Using a 2imes2imes2 factor
arXiv:2602.01053v2 Announce Type: replace Abstract: Role specialization in multi-LLM agent systems is often realized via multi-LoRA, where agents share a pretrained backbone and differ only by lightwe
arXiv:2510.00481v2 Announce Type: replace-cross Abstract: In 2025, Large Language Model (LLM) services have launched a new feature -- AI video chat -- allowing users to interact with AI agents via rea
arXiv:2606.00820v1 Announce Type: new Abstract: Multi-agent debate (MAD) is a promising strategy for improving LLM reasoning, but when agents converge on a shared answer, it is unclear whether that co
arXiv:2603.12109v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a de facto paradigm for building LLM-based agents that act, interact, and reason over extended task horizons.
arXiv:2606.01042v1 Announce Type: cross Abstract: Perturbation experiments are central to understanding cellular mechanisms, but remain costly and sparse, motivating prediction of gene expression resp
arXiv:2606.00494v1 Announce Type: new Abstract: Post-Training Quantization (PTQ) and Low-Rank Adaptation (LoRA) constitute the standard pipeline for efficient Large Language Model (LLM) deployment. Ho
arXiv:2512.07795v2 Announce Type: replace Abstract: Benchmark scores for LLM reasoning systems are reported as single numbers, yet the same model, strategy, and task can produce meaningfully different
arXiv:2606.01991v1 Announce Type: new Abstract: As Large Language Model (LLM) agents increasingly leverage the Model Context Protocol (MCP) to operate in complex environments, the expansion of their a
// Scaling Behavior of Single LLM-Driven Multi-Agent Systems // Does adding more agents actually make a multi-agent system better? It's possible that collective intelligence emerges from interaction d
arXiv:2606.02355v1 Announce Type: new Abstract: Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rely on external skill generators during training or pe
arXiv:2606.01311v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on reusable external skills to solve long-horizon interactive tasks. Existing training-free skill
🌞This is big Local AI news! A new open-source Computer-Use LLM has just launched. Holo 3.1 is H Company’s (🇫🇷) new local computer-use agent model that beats Qwen3.5-397B, Kimi-K2.5, and Sonnet 4.6! Si
arXiv:2606.00516v1 Announce Type: new Abstract: Mixed batching (MB)--interleaving prefill and decode in a single batch--has become the standard scheduling strategy for large language model (LLM) infer
arXiv:2505.22961v3 Announce Type: replace Abstract: Large language models (LLMs) have shown promising potential in persuasion, but existing works on training LLM persuaders are still preliminary. Nota
arXiv:2606.02304v1 Announce Type: new Abstract: LLM-based agents can solve multi-step interactive tasks by combining reasoning with environment feedback, yet each episode starts from the same fixed co
arXiv:2512.00956v3 Announce Type: replace Abstract: Quantizing LLM weights and activations is a standard approach for efficient deployment, but a few extreme outliers can stretch the dynamic range and
arXiv:2605.30504v1 Announce Type: new Abstract: LLM benchmark labels are frozen at release and silently propagated into downstream benchmarks, errors and all. We introduce an Item Response Theory-base
arXiv:2605.30653v1 Announce Type: new Abstract: Multi-agent LLM systems often treat agreement as evidence: when many agents in a panel give the same answer, that answer is assumed to be more reliable.
arXiv:2605.30568v1 Announce Type: new Abstract: LLM-as-a-Judge is a scalable alternative to human evaluation, yet existing rubric-based methods rely on human-annotated data such as reference answers o
arXiv:2605.30621v1 Announce Type: new Abstract: LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task
arXiv:2409.14583v4 Announce Type: replace Abstract: LLM bias evaluation is critical as large language models (LLMs) increasingly influence high-stakes decisions. This paper provides a comprehensive as
arXiv:2605.30571v1 Announce Type: cross Abstract: Physical AI systems, including robots, autonomous vehicles, embodied agents and edge copilots, often run a different inference workload from cloud LLM
arXiv:2605.31287v1 Announce Type: cross Abstract: Managers in manufacturing settings rely on digital interfaces to interpret operational data for decision-making, but growing data volume and complexit
slowly we're all realizing that tools should be called from code, not from within the llm api Introducing Search as Code, our new search architecture for AI agents. It writes Python that calls our sea
arXiv:2605.30628v1 Announce Type: cross Abstract: Universal LLM reliability is not a finite-library problem: across all possible tasks, tools, schemas, knowledge sources, and evaluator expectations, n
These are some of my LLM assisted contributions from the past month. Nothing amazing, but I'm slowly getting better at it. Atm, using Qwen3.6 27B exclusively. For hardware - switching between M2 Ultra
I did a talk on LLM Wikis and HTML artifacts recently, if you are curious to learn more on the topic: https://academy.dair.ai/events/cmovobp97000904l5h0n9a2yz Doing a second session and a few releases
arXiv:2605.29910v1 Announce Type: cross Abstract: Consensus protocols form the backbone of distributed systems and blockchains, where implementation bugs can cause data corruption and financial losses
ComfyUI just added @OpenRouter support. Instead of being locked into a single LLM, you can now access 20+ models directly inside Comfy. More flexibility, less friction, same workflow. Links to the wor
arXiv:2605.30200v1 Announce Type: new Abstract: The double-edged sword of integrating Large Language Models (LLMs) requires an effective triadic collaboration mechanism among LLMs, teachers and studen
arXiv:2511.08949v2 Announce Type: replace Abstract: High-quality datasets are critical for training and evaluating reliable NLP models. In tasks like natural language inference (NLI), human label vari
arXiv:2605.29874v1 Announce Type: cross Abstract: Do next-generation LLM agents inherit the cooperative biases documented in their predecessors, or does scale and provider diversity reshape equilibriu
arXiv:2605.29790v1 Announce Type: cross Abstract: LLM-based multi-agent systems (MAS) have emerged as an effective paradigm for complex and long-horizon tasks. However, in real-world tasks, MAS often
arXiv:2605.29394v1 Announce Type: new Abstract: While large language models (LLMs) excel at static scientific reasoning, they struggle to model the temporal structure of dynamic physical processes. We
arXiv:2601.21909v2 Announce Type: replace Abstract: Current LLM post-training methods optimize complete reasoning trajectories through Supervised Fine-Tuning (SFT) followed by outcome-based Reinforcem
arXiv:2601.08654v2 Announce Type: replace-cross Abstract: Rubric-based text evaluation increasingly uses large language models (LLMs) as scalable judges, but aligning frozen black-box models with huma
arXiv:2605.29668v1 Announce Type: new Abstract: LLM agents acting in structured environments fail in operational rather than conversational ways, and reliability depends on procedural knowledge of the
arXiv:2508.05614v2 Announce Type: replace-cross Abstract: LLM agents achieve 85-96% success on tasks where instructions fully specify the action, but drop to 29-53% when action feasibility depends on
arXiv:2605.29963v1 Announce Type: cross Abstract: Honeypots are decoy systems mimicking real system components designed to defend against cyber attacks. Recently, LLMs increasingly serve as simulation
arXiv:2605.28840v1 Announce Type: cross Abstract: Large language model (LLM) agents with tool-calling capabilities are increasingly deployed in production systems, yet a fundamental reliability questi
LangSmith LLM Gateway is a feature that enables proactive cost and privacy controls by enforcing spending limits and redacting personally identifiable information (PII) before API requests are sent to
arXiv:2605.28999v1 Announce Type: cross Abstract: LLMs are vulnerable to prompt injection attacks. However, this vulnerability has been primarily demonstrated conceptually in academic studies or throu
arXiv:2605.30159v1 Announce Type: new Abstract: Memory-augmented LLM agents tackle complex long-horizon tasks by recursively summarizing interaction trajectories into compact memory. However, existing
arXiv:2605.29800v1 Announce Type: new Abstract: LLM-as-a-judge panels aggregate votes from multiple models, with the expectation that diverse models yield more reliable evaluations. We develop a frame
arXiv:2605.30148v1 Announce Type: cross Abstract: Evolution Strategies (ES) has recently emerged as a competitive alternative to reinforcement learning (RL) for large language model (LLM) fine-tuning,
arXiv:2605.29313v1 Announce Type: new Abstract: LLM multi-agent systems often coordinate through natural-language dialogue or loosely structured shared memory, making intermediate state difficult to v
pibot is now running fully local, using parakeet for STT, qwen3-tts for TTS, and Qwen 3.6 as the local multi-modal LLM via llama.cpp. The STT and TTS inference engines are Rust/mlx-c based. Ported fro
arXiv:2605.29156v1 Announce Type: cross Abstract: Pointwise reward modeling offers critical signals for LLM post-training, yet struggles with absolute scoring in subjective, non-verifiable settings. R
arXiv:2602.01869v3 Announce Type: replace Abstract: LLM-driven agents excel at sequential decision-making but often rely on on-the-fly reasoning, re-deriving solutions even in recurring scenarios. Thi
arXiv:2605.29794v1 Announce Type: new Abstract: LLM agents now draw on growing skill libraries to handle complex tasks. However, injecting more skills does not always improve task completion and can e
arXiv:2605.28966v1 Announce Type: new Abstract: Large language model (LLM) leaderboards rank AI models using standardized benchmarks and have become highly visible across computer science, despite kno
arXiv:2605.29141v1 Announce Type: cross Abstract: Traditional recommender systems (RecSys) primarily infer user preferences from implicit signals (such as clicks, watches, and purchases), often neglec
arXiv:2605.27744v1 Announce Type: new Abstract: Multi-agent LLM systems have become the dominant production workload, but the serving stack was not built for them. The agent framework above knows agen
arXiv:2512.17375v2 Announce Type: replace-cross Abstract: LLM-as-a-Judge systems supply the reward signal in modern RLHF and RLVR pipelines, but their binary verdict reduces to a single linear readout
arXiv:2605.27668v1 Announce Type: cross Abstract: Probabilistic forecasting estimates the likelihood of uncertain future events. To improve LLM forecasting, existing methods typically learn from binar
arXiv:2605.28666v1 Announce Type: new Abstract: In modern industry, dynamic environments and the complexity of modular and reconfigurable resources require automated planning of process sequences. Cap