Knowledge catalogue
arXiv:2603.19453v2 Announce Type: replace Abstract: We study LLM policy synthesis: using a language model to iteratively generate programmatic agent policies for multi-agent environments. Rather than
arXiv:2606.01435v1 Announce Type: new Abstract: LLM-based memory systems increasingly maintain facts that evolve over time, where a recurring failure is conflict resolution: when a fact has multiple c
arXiv:2606.01730v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as heuristic advisors for black-box optimization, yet their suggestions and self-reported confidence
arXiv:2602.05395v2 Announce Type: replace-cross Abstract: A simple strategy for improving LLM accuracy, especially in math and reasoning problems, is to sample multiple responses and submit the answer
arXiv:2605.30919v1 Announce Type: cross Abstract: The rapid development of large language models (LLMs) has raised concerns on the use of inappropriate data for training, which has led to a growing in
arXiv:2605.30152v1 Announce Type: cross Abstract: Proactive agents read user activity as text and call an LLM on every event to decide whether to act. But user activity is not natively text: it is a s
arXiv:2605.30335v1 Announce Type: new Abstract: Multi-component LLM agents assemble probabilistic claims from components that each see only part of a joint problem; the composition can violate basic p
arXiv:2605.28850v1 Announce Type: new Abstract: We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments. Using TradeArena, an
When you are talking to an LLM, you are speaking to a synthesized work of interactive fiction, not a real being. ChatGPT, Claude, and Sydney are not their neural networks. If any LLM claims to be cons
arXiv:2605.28183v1 Announce Type: cross Abstract: We introduce the BenGER (Benchmark for German Law) dataset for evaluating LLM systems on subsumption-based legal reasoning in German law. The BenGER d
Beyond being fast, LiteParse is designed to provide highly accurate, semantically coherent text for LLM use. We benchmarked every open-source, model-free PDF parser on LLM QA tasks - from PyPDF to PyM
arXiv:2502.12468v2 Announce Type: replace-cross Abstract: The LLM-as-a-Judge paradigm shows promise for evaluating generative content but lacks reliability in reasoning-intensive scenarios, such as pr
arXiv:2605.27429v1 Announce Type: cross Abstract: Industrial video-on-demand (VOD) recommenders need richer content understanding, but LLM-as-reranker designs repeat prompt construction, token generat
arXiv:2605.28647v1 Announce Type: new Abstract: It is well known that LLM guardrails and trained persona dynamics can produce a reality gap: the distance between the world a LLM is permitted or shaped
arXiv:2510.06843v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have exhibited impressive capabilities across diverse application domains. Recent work has explored Multi-LLM Age
arXiv:2605.26156v1 Announce Type: cross Abstract: The known stylistic biases in LLM judges, such as a preference for verbosity or specific sentence structures, present an underexplored security vulner
arXiv:2603.28345v2 Announce Type: replace-cross Abstract: LLM API calls are becoming a ubiquitous program construct, yet they create a boundary that no existing program analysis can cross: runtime val
LangSmith's LLM Gateway is a cost control and monitoring tool designed to prevent unexpected high spending on LLM API calls by providing observability and likely rate-limiting or budget-cap features.
arXiv:2605.22976v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly integrated into software systems for diverse purposes, due to their versatility, flexibility, and abilit
arXiv:2605.23102v1 Announce Type: cross Abstract: Large language models (LLMs) offer a scalable mechanism to elicit domain-informed prior information for high-dimensional variable selection. However,
arXiv:2605.23296v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate growing conversation histories that eventually exceed the model's context window. Context compaction via LLM-based su
arXiv:2605.22855v1 Announce Type: cross Abstract: Personalized pricing negotiations are a challenging testbed for LLM agents because successful interaction does not guarantee profitable decision makin
arXiv:2605.21768v1 Announce Type: new Abstract: Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions.
arXiv:2512.09472v2 Announce Type: replace-cross Abstract: Deploying multiple models within shared GPU clusters is a key strategy to improve resource efficiency in large language model (LLM) serving. E
arXiv:2605.21427v1 Announce Type: new Abstract: Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and energy consumption.
arXiv:2605.21748v1 Announce Type: new Abstract: As interactive LLM-based applications are created and refined, model developers need to evaluate the quality of generated text along many possible axes.
Learn how to design, calibrate, and run LLM-as-a-judge evaluators with fixed labels, human agreement checks, trace context, and Phoenix Evals. The post How to build LLM-as-a-Judge evaluators that hold
arXiv:2605.18890v1 Announce Type: cross Abstract: The scientific claims drawn from LLM social simulations should be no stronger than the robustness audits that support them. Generative agents bring ne
arXiv:2601.20309v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) serving faces a fundamental tension between stringent latency Service Level Objectives (SLOs) and limited GPU memor
arXiv:2605.18859v1 Announce Type: cross Abstract: LLM routing matters most in long-horizon applications such as coding agents, deep research systems, and computer-use agents, where a single user reque
arXiv:2508.08501v3 Announce Type: replace Abstract: We introduce GVGAI-LLM, a video game benchmark for evaluating the reasoning and problem-solving capabilities of large language models (LLMs). Built
arXiv:2504.07347v3 Announce Type: replace-cross Abstract: As demand for Large Language Models (LLMs) and AI agents grows rapidly, optimizing systems for efficient LLM inference becomes critical. While
arXiv:2605.16142v1 Announce Type: new Abstract: LLMs have shown impressive success in program synthesis, discovering programs that surpass prior solutions. However, these approaches rely on simple num
“Dependably for LLM agent failures” @hwchase17 Started on this and finding it awesome; also LangSmith engine sparked an idea. The 'Dependabot like for LLM agent failures'. LangSmith Engine gives you t
arXiv:2605.14051v1 Announce Type: new Abstract: Industrial LLM agent systems often separate planning from execution, yet LLM planners frequently produce structurally invalid or unnecessarily long work
arXiv:2605.13496v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become increasingly prevalent in cloud-based platforms, propelled by the introduction of AI-based consumer and enter
arXiv:2605.12487v1 Announce Type: new Abstract: We explore the effectiveness of an LLM-guided query refinement paradigm for extending the usability of embedding models to challenging zero-shot search
arXiv:2605.08382v1 Announce Type: cross Abstract: LLM coding agents now generate code at an unprecedented scale, yet LLM-generated code introduces cybersecurity vulnerabilities into codebases without
arXiv:2605.09227v1 Announce Type: new Abstract: [Abridged] Using a Large Language Model (LLM) as an automatic rater (LLM-as-a-judge) is cheap but potentially biased: some judges run lenient, others st
This works really well btw, at the end of your query ask your LLM to 'structure your response as HTML', then view the generated file in your browser. I've also had some success asking the LLM to prese
arXiv:2605.04886v1 Announce Type: new Abstract: This position paper argues that the under-representation of social science tasks in contemporary LLM benchmarks limits advances in both LLM evaluation a
arXiv:2605.04539v1 Announce Type: new Abstract: Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference si
arXiv:2605.01143v1 Announce Type: new Abstract: Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, the
arXiv Papers → LLM Artifacts This is how I keep up with AI research now. It's like having access to the most personalized arXiv feed. Automations run everyday to curate papers based a set of rules and
arXiv:2505.16120v2 Announce Type: replace Abstract: The emergence of Large Language Models (LLMs) has reshaped agent systems. Unlike traditional rule-based agents with limited task scope, LLM-powered
arXiv:2605.03723v1 Announce Type: new Abstract: The rise of large language models (LLMs) has created an urgent need to distinguish between human-written and LLM-generated text to ensure authenticity a
arXiv:2604.25224v2 Announce Type: replace Abstract: LLM-based financial agents increasingly produce investment rationales before the outcomes needed to evaluate them are observable. This creates a del
arXiv:2605.01461v1 Announce Type: new Abstract: Swarm foraging algorithms, such as the central-place foraging algorithm (CPFA), typically rely on offline parameter optimization using genetic algorithm
arXiv:2605.01687v1 Announce Type: new Abstract: We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic
arXiv:2602.18700v2 Announce Type: replace-cross Abstract: LLM agents rely heavily on high-quality trajectory data to guide their problem-solving behaviors, yet producing such data requires substantial
arXiv:2505.23723v2 Announce Type: replace Abstract: The emergence of large language model (LLM)-based agents has significantly advanced the development of autonomous machine learning (ML) engineering.
arXiv:2604.27345v1 Announce Type: new Abstract: Human annotators frequently disagree on emotion labels, yet most evaluations of Large Language Model (LLM) emotion annotation collapse these judgments i
LLM 0.32a0 is an alpha release of Simon Willison's LLM Python library and CLI tool for accessing large language models, featuring consequential architectural changes. The release includes two key chan
arXiv:2604.23072v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly tasked with complex real-world analysis (e.g., in financial forecasting, scientific discovery), yet t
arXiv:2604.23178v1 Announce Type: new Abstract: LLM-as-a-Judge has become the dominant paradigm for evaluating language model outputs, yet LLM judges exhibit systematic biases that compromise evaluati
arXiv:2604.23283v1 Announce Type: new Abstract: Current LLM agents operate under an implicit but universal assumption: execution is a transaction -- the user submits a request, the agent works in isol
arXiv:2604.23505v1 Announce Type: cross Abstract: Uncertainty in large language model (LLM)-based systems is often studied at the level of a single model output, yet deployed LLM applications are comp
arXiv:2604.21276v1 Announce Type: cross Abstract: As pretrained large language models replace task-specific decoders in speech recognition, a critical question arises: do their text-derived priors mak
arXiv:2604.20273v1 Announce Type: new Abstract: We present ActuBench, a multi-agent LLM pipeline for the automated generation and evaluation of advanced actuarial assessment items aligned with the Int
arXiv:2604.19984v1 Announce Type: cross Abstract: Research has documented LLMs' name-based bias in hiring and salary recommendations. In this paper, we instead consider a setting where LLMs generate c