Knowledge catalogue
arXiv:2603.29002v2 Announce Type: replace-cross Abstract: Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse atte
When is the last time a general purpose LLM (putting aside hybrid systems like Claude Code with special purpose symbolic harnesses) last completely blew away all competing prior models? GPT-4 relative
arXiv:2605.08563v1 Announce Type: new Abstract: When an LLM agent fails a multi-step tool-augmented task and retries, the failed attempt typically remains in its context window -- contaminating the ne
arXiv:2605.09360v1 Announce Type: cross Abstract: Execution-based evaluation of LLM-generated code implicitly treats successful execution as a proxy for correctness. In scientific simulation, this pro
arXiv:2605.05703v2 Announce Type: replace-cross Abstract: Optimizing the communication structure of large language model based multi-agent systems (LLM-MAS) has been shown to improve downstream perfor
Am old enough to remember when @GeoffreyHinton told me I was stupid for saying that LLMs regurgitate training data. He was wrong. LLM regurgitation is now one of the best-established findings in the f
arXiv:2605.06939v1 Announce Type: new Abstract: LLM-as-a-Judge evaluation has become a standard tool for assessing base model performance. However, characterizing performance via the naive estimator,
arXiv:2605.07985v1 Announce Type: cross Abstract: Selecting the optimal LLM inference configuration requires evaluation across hardware, serving engines, attention backends, and model architectures, s
arXiv:2605.07247v1 Announce Type: new Abstract: Scalable AI agents training relies on interactive environments that faithfully simulate the consequences of agent actions. Manually crafted environments
arXiv:2605.06669v1 Announce Type: cross Abstract: Educational LLM tutors face a core AI alignment challenge: they must follow user intent while preserving pedagogical constraints and safety policies.
arXiv:2510.16079v2 Announce Type: replace-cross Abstract: Current Large Language Model (LLM) agents show strong performance in tool use, but lack the crucial capability to systematically learn from th
arXiv:2508.16571v4 Announce Type: replace Abstract: In this paper, we describe and benchmark a competitor-discovery component used within an agentic AI system for fast drug asset due diligence. A comp
arXiv:2605.07723v1 Announce Type: cross Abstract: Large language models (LLMs) are known to generate plausible but false information across a wide range of contexts, yet the real-world magnitude and c
arXiv:2605.07342v1 Announce Type: cross Abstract: Compile-pass rate is the dominant evaluation signal for LLM code generation, yet for multi-component domain-specific artifacts it can be actively misl
arXiv:2605.06623v1 Announce Type: cross Abstract: Large language model (LLM)-based Multi-agent systems (MAS) have shown promise in tackling complex collaborative tasks, where agents are typically orch
Simon Willison discovered how to use an LLM command-line interface tool in Unix shebang lines, enabling the creation of executable scripts written in English or natural language. This technique allows
arXiv:2605.06914v1 Announce Type: cross Abstract: Recent methods expose intra-request parallelism in LLM outputs, allowing independent branches to decode concurrently. Existing serving systems execute
arXiv:2605.07840v1 Announce Type: new Abstract: Relational learning is a challenging problem that has motivated a wide range of approaches, including graph-based models (e.g., graph neural networks, g
arXiv:2605.07331v1 Announce Type: cross Abstract: Reinforcement learning, including reinforcement learning with verifiable rewards (RLVR), has emerged as a powerful approach for LLM post-training. Cen
arXiv:2605.07129v1 Announce Type: cross Abstract: Large Language Models (LLMs) have emerged as a promising paradigm for next-generation recommender systems, offering strong semantic understanding and
arXiv:2605.07102v1 Announce Type: new Abstract: Evaluating literary quality requires assessing interpretive dimensions such as cultural representation, emotional depth, and philosophical sophisticatio
arXiv:2605.06908v1 Announce Type: cross Abstract: Adaptive test-time compute for LLM agents aims to invoke extra computation only when it improves performance. Existing methods typically use confidenc
arXiv:2508.10880v3 Announce Type: replace-cross Abstract: The widespread deployment of LLM-based agents is likely to introduce a critical privacy threat: malicious agents that proactively engage other
arXiv:2605.07507v1 Announce Type: new Abstract: The exponential growth of academic publications has created an urgent need for automated tools capable of extracting structured knowledge from unstructu
// The Memory Curse in LLM Agents // (bookmark it) Long histories apparently degrades agents as they become increasingly history-following and risk-minimizing. Across 7 LLMs and 4 social dilemma games
arXiv:2605.07186v1 Announce Type: cross Abstract: Existing Large Language Model (LLM) benchmarks primarily focus on syntactically correct inputs, leaving a significant gap in evaluation on imperfect t
arXiv:2605.06812v1 Announce Type: new Abstract: LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and mult
arXiv:2605.07395v1 Announce Type: cross Abstract: Efficient routing across multiple LLMs enables cost-quality tradeoffs by directing queries to the cheapest capable model. Prior work attributes routin
Tip of the day: You can use Hermes Agent's Credential Pools to login or add multiple API keys for the same LLM Provider and it will rotate across them to ensure stability of your operations. Learn mor
arXiv:2605.04595v1 Announce Type: new Abstract: The rapid adoption of large language models (LLMs) has created significant challenges for efficient inference at scale. Unlike traditional workloads, LL
Anthropic: Anthropic researchers detail “natural language autoencoders”, which convert LLM activations, the numbers encoding a model's thoughts, into natural language text — When you talk to an AI mod
arXiv:2605.03205v1 Announce Type: cross Abstract: Large language models (LLMs) are rapidly changing how researchers in materials science and chemistry discover, organize, and act on scientific knowled
arXiv:2605.04956v1 Announce Type: new Abstract: LLM-based Triton kernel generation has attracted significant interest, yet a fundamental empirical question remains unanswered: where does this capabili
Ramp Labs is doing a ton of cool work all the way from launching products to hardcore research on LLM internals, this is a fun one 🔥 Talked to @ramplabs Head of Applied Research Alex Shevchenko on the
arXiv:2605.04913v1 Announce Type: new Abstract: LLM post-training typically propagates task gradients through the full depth of the model. Although this end-to-end structure is simple and general, it
arXiv:2605.03353v1 Announce Type: cross Abstract: LLM-Agents have evolved into autonomous systems for complex task execution, with the SKILL.md specification emerging as a de facto standard for encaps
arXiv:2602.00305v2 Announce Type: replace-cross Abstract: LLM-based vulnerability detectors are increasingly deployed in CI/CD security gating, yet their resilience to evasion under syntax- and compil
arXiv:2602.12631v2 Announce Type: replace-cross Abstract: Inventory control is a fundamental operations problem in which ordering decisions are traditionally guided by theoretically grounded operation
arXiv:2603.10384v2 Announce Type: replace Abstract: Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework th
arXiv:2502.18414v2 Announce Type: replace Abstract: Generalized Category Discovery (GCD) is a practical and challenging open-world task that aims to recognize both known and novel categories in unlabe
arXiv:2605.02199v1 Announce Type: new Abstract: Long-term LLM agents must compress streams of past interactions into persistent memory before future queries are known. Existing evaluations usually mea
We have greatly expanded the surface area for plugins over the last few weeks, and now you can extend LLM Inference Providers and Gateway Channels with plugins. Want a custom implementation of your fa
arXiv:2605.02463v1 Announce Type: cross Abstract: Multi-agent LLM systems are increasingly used to solve complex tasks through decomposition, debate, specialization, and ensemble reasoning. However, t
Wiki-Builder, a tool for creating LLM-powered wikis, was featured on Hacker News' front page, announced by DAIR.AI. The post indicates upcoming updates and improvements to make wiki creation more acce
arXiv:2605.01292v1 Announce Type: new Abstract: The growing spread of misinformation in digital media highlights the need for reliable fake news detection systems, yet progress in under-resourced lang
arXiv:2605.00136v1 Announce Type: new Abstract: Tool-augmented reasoning has become a popular direction for LLM-based agents, and it is widely assumed to improve reasoning and reliability. However, we
arXiv:2605.01006v1 Announce Type: new Abstract: Partisan news media erode cross-partisan trust, but large language models (LLMs) offer a potential means of debiasing such content at scale. Across two
arXiv:2605.02600v1 Announce Type: new Abstract: While Large Language Models (LLMs) and Vision-Language Models (VLMs) demonstrate remarkable capabilities in high-level reasoning and semantic understand
arXiv:2603.01865v3 Announce Type: replace Abstract: LLM-as-judge evaluation has become standard practice for open-ended model assessment; however, judges exhibit systematic biases that cannot be avera
arXiv:2601.21714v2 Announce Type: replace Abstract: The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requir
arXiv:2605.00433v1 Announce Type: cross Abstract: Code generation, which aims to automatically generate source code from given programming requirements, has the potential to substantially improve soft
arXiv:2605.01350v1 Announce Type: new Abstract: Detecting machine-generated text is essential for transparency and accountability when deploying large language models (LLMs). Among detection approache
arXiv:2604.06091v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly acting as human delegates in multi-agent environments, where a representative agent integrates di
arXiv:2605.01133v1 Announce Type: cross Abstract: Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on compl
claudely is a tool that enables users to run Claude Code against local LLM providers such as LM Studio, Ollama, or llama.cpp while preserving their existing Claude configuration. The tool allows devel
arXiv:2605.00238v1 Announce Type: new Abstract: Automated short answer grading (ASAG) with large language models (LLMs) is commonly evaluated with aggregate metrics such as macro-F1 and Cohen's kappa.
If you need proof of why AI output can't be trusted by default watch that page for more than 1 minute for any given LLM that produces output in there. An amazing time capsule of the unevenness of curr
arXiv:2604.01707v2 Announce Type: replace Abstract: Memory emerges as the core module in the large language model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game pla
arXiv:2605.00419v1 Announce Type: cross Abstract: Model ensembling is a well-established technique for improving the performance of machine learning models. Conventionally, this involves averaging the
arXiv:2605.00553v1 Announce Type: new Abstract: Large Language Model (LLM) Red-Teaming, which proactively identifies vulnerabilities of LLMs, is an essential process for ensuring safety. Finding effec