llm 0.31.1
Release: llm 0.31.1 Fix for a bug with OpenAI Chat Completion endpoints where a tool call with empty arguments could result in a JSON error from some providers. #1521 This bug came up when I was testi
Knowledge catalogue
Release: llm 0.31.1 Fix for a bug with OpenAI Chat Completion endpoints where a tool call with empty arguments could result in a JSON error from some providers. #1521 This bug came up when I was testi
arXiv:2607.05458v1 Announce Type: cross Abstract: Large language model (LLM) agents are usually improved by changing prompts, models, or hand-written workflows, while the execution harness around the
arXiv:2607.04412v1 Announce Type: new Abstract: Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals. W
arXiv:2607.05391v1 Announce Type: new Abstract: Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we id
arXiv:2411.07447v5 Announce Type: replace-cross Abstract: LLMs are increasingly used world-wide from daily tasks to agentic systems and data analytics, requiring significant GPU resources. While LLM i
arXiv:2607.03695v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed in interacting populations, raising the question of what such populations come to believe co
arXiv:2607.01678v1 Announce Type: new Abstract: Communication increasingly dominates the cost of Large Language Model (LLM) pre-training, especially under data-parallel and sharded training schemes, w
arXiv:2601.23088v2 Announce Type: replace-cross Abstract: Semantic caching has emerged as a pivotal technique for scaling LLM applications, widely adopted by major providers including AWS and Microsof
arXiv:2606.31801v1 Announce Type: new Abstract: Automated Heuristic Design (AHD) with Large Language Models (LLMs) has shown remarkable progress in discovering high-quality heuristics. However, existi
arXiv:2606.29985v1 Announce Type: new Abstract: Diversity in LLM mathematical reasoning is critical for exploration, but common diversity metrics mostly capture surface-level variation rather than dif
arXiv:2602.10233v2 Announce Type: replace-cross Abstract: LLM-guided evolutionary computation, most notably AlphaEvolve, has been remarkably successful in discovering novel mathematical constructions
arXiv:2606.29030v1 Announce Type: new Abstract: AI agents extend conventional large language model (LLM) applications by integrating language understanding with task execution, external tool use, and
arXiv:2601.16956v1 Announce Type: cross Abstract: The rapid growth of Large Transformer-based models, specifically Large Language Models (LLMs), now scaling to trillions of parameters, has necessitate
arXiv:2606.27806v1 Announce Type: new Abstract: World models for language agents come in two useful forms. An agent-based world model calls an LLM API and reasons flexibly in language, but its errors
arXiv:2606.26924v1 Announce Type: cross Abstract: LLM coding harnesses grant agents broad file and shell access, yet the configuration layer that steers them -- rules files, agent definitions, IDE-spe
arXiv:2606.20632v2 Announce Type: replace-cross Abstract: Multi-LLM systems use multiple language models to deliberate, judge each other's outputs, or coordinate as agents. Their value depends on the
arXiv:2510.25850v3 Announce Type: replace-cross Abstract: We introduce Debate2Create (D2C), a multi-agent LLM framework that formulates robot co-design as structured, iterative debate grounded in phys
arXiv:2606.16821v2 Announce Type: replace Abstract: Large language model (LLM)-based search agents synthesize open-web content into actionable recommendations on behalf of users, creating a risk that
arXiv:2606.24605v1 Announce Type: new Abstract: Accurate user modeling often depends on rich interaction histories, which are unavailable for billions of low-activity users. Large Language Models (LLM
arXiv:2503.00069v2 Announce Type: replace-cross Abstract: Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values -
arXiv:2506.04018v3 Announce Type: replace-cross Abstract: As Large Language Model (LLM) agents become more widespread, associated misalignment risks increase. While prior research has studied agents'
arXiv:2606.20668v1 Announce Type: cross Abstract: LLM supervision systems, namely input/output moderation filters and jailbreak detectors, are the primary safeguard against misuse in deployed AI appli
arXiv:2606.20820v1 Announce Type: new Abstract: Can we trust evaluation scores to capture an LLM's true real-world performance? Certifiable evaluation answers this question by providing guarantee for
arXiv:2606.23521v1 Announce Type: cross Abstract: Long-running LLM agents keep valuable state resident on GPUs: KV caches, request schedulers, communication state, and sometimes online adapters. Losin
arXiv:2606.23136v1 Announce Type: cross Abstract: Finding the shortest path in non-geometric network graphs, where edge weights encode arbitrary metrics such as latency or monetary cost rather than sp
arXiv:2606.18774v2 Announce Type: replace Abstract: We present RouteJudge, an online pairwise preference evaluation framework for LLM routing systems, with a public platform available at https://route
arXiv:2606.11916v1 Announce Type: cross Abstract: This paper proposes an empirical methodology to study software aging in GPU-based LLM serving systems. Traditional aging studies focus on CPU-centric
arXiv:2606.11976v1 Announce Type: cross Abstract: Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue. Most AI agents explore repos
arXiv:2606.11416v1 Announce Type: cross Abstract: Repository-level benchmarks for evaluating Large Language Model (LLM) code repair on Secure Multi-Party Computation (MPC) software do not yet exist, a
arXiv:2606.12071v1 Announce Type: cross Abstract: LLMs are increasingly used to generate and judge scientific ideas. This makes novelty evaluation a central problem. Full idea evaluation is difficult
arXiv:2606.12117v1 Announce Type: cross Abstract: Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.g., on the model's ability to follow specific for
arXiv:2601.22025v2 Announce Type: replace-cross Abstract: Evaluating Large Language Model (LLM) applications differs from conventional software testing because outputs are probabilistic, semantically
arXiv:2606.10307v1 Announce Type: new Abstract: Evaluating reasoning quality in multi-agent LLM systems is challenging, especially for open-ended tasks without reference answers. We investigate whethe
arXiv:2606.09863v1 Announce Type: new Abstract: LLM agents can fail silently by asserting task completion when the environment state shows otherwise. We study this failure mode, false success, across
arXiv:2606.09900v1 Announce Type: cross Abstract: Long-term memory is the missing layer for LLM agents: across sessions they forget, and the common workaround -- replaying the whole history into the p
arXiv:2507.17188v2 Announce Type: replace-cross Abstract: This paper investigates secure communications in rate-splitting multiple access (RSMA) enabled heterogeneous UAV networks, where multiple UAVs
arXiv:2606.09613v1 Announce Type: cross Abstract: Multi-turn LLM agents interleave model calls with external tool invocations, shifting serving from stateless request processing to stateful program ex
arXiv:2606.09520v1 Announce Type: cross Abstract: Can a general-purpose large language model design molecules with the precision of a seasoned chemist? Current LLM-based frameworks answer this questio
arXiv:2606.08661v1 Announce Type: cross Abstract: Data agents integrate LLM-driven reasoning with relational data access, executable analytical tools, and multi-step workflow orchestration, making the
arXiv:2606.09738v1 Announce Type: new Abstract: Text-driven indoor scene generation and editing require an intermediate representation that language models can both produce and revise. Existing LLM-ba
arXiv:2601.21816v2 Announce Type: replace Abstract: Evaluating the performance of large language models (LLMs) from human preference data is crucial for obtaining LLM leaderboards. However, many exist
arXiv:2604.07472v2 Announce Type: replace Abstract: Serving large language model (LLM) inference in cloud environments requires jointly optimizing model selection, GPU provisioning, parallelism config
arXiv:2606.06781v1 Announce Type: new Abstract: High accuracy does not necessarily make an LLM a faithful coder. This issue matters because many social-science studies rely on expert-written codebooks
arXiv:2606.05548v1 Announce Type: cross Abstract: The rapid proliferation of Agent Development Kits (ADKs), SDK-level frameworks for building LLM-powered autonomous agents, has outpaced any empirical
arXiv:2606.06256v1 Announce Type: new Abstract: As the input length of large language model (LLM) serving continues to grow, the KV cache has become a dominant bottleneck in AI infrastructure. It limi
arXiv:2606.05384v1 Announce Type: cross Abstract: LLM-as-judge evaluation is widely used in benchmarking pipelines, where model outputs are compared and ranked using automated evaluators. These pipeli
arXiv:2606.04272v1 Announce Type: new Abstract: The standard LLM training pipeline applies reinforcement learning (RL) only after pre-training and supervised fine-tuning (SFT). We question this status
arXiv:2606.03895v1 Announce Type: cross Abstract: Large language model (LLM) agents are evolving from request-response assistants into long-running software actors: they maintain state across model ca
arXiv:2605.11954v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in social science as scalable measurement tools for converting unstructured text into variables t
arXiv:2606.03108v1 Announce Type: new Abstract: Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, wher
arXiv:2606.03698v1 Announce Type: new Abstract: A central goal of large language model (LLM) research is to build agentic systems that can plan, act, and adapt through sustained interaction with dynam
arXiv:2606.03866v1 Announce Type: cross Abstract: Scaling recommender systems via large language models (LLMs) has become a prominent trend in the industry. However, aligning the LLM's semantic space
arXiv:2606.01629v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used for long-form generation, reliably evaluating long-form outputs has become a critical challenge. L
arXiv:2602.11641v2 Announce Type: replace Abstract: Text-attributed graphs (TAGs) associate nodes with textual attributes and graph structure, enabling GNNs to jointly model semantic and structural in
arXiv:2603.00829v2 Announce Type: replace-cross Abstract: Safe deployment of Large Language Model (LLM) agents in autonomous settings requires reliable oversight mechanisms. A central challenge is det
arXiv:2606.00846v1 Announce Type: new Abstract: Users increasingly face the challenge of selecting an appropriate LLM for a given task from a rapidly growing pool of LLMs, each with distinct but often
arXiv:2606.01365v1 Announce Type: new Abstract: Tool-using multi-agent large language model (LLM) systems spend computation through model tokens, tool calls, retries, and code execution before produci
arXiv:2512.16167v3 Announce Type: replace-cross Abstract: Decentralized LLM-based multi-agent service economies face three vulnerabilities that undermine traditional trust mechanisms: reduced cost of
arXiv:2606.01041v1 Announce Type: new Abstract: Experience learning has achieved promising results in enhancing LLM agent planning and reasoning by integrating past interactions as reusable knowledge.
arXiv:2606.00765v1 Announce Type: new Abstract: LLM-based agents increasingly solve complex tasks through long trajectories involving reasoning steps, tool calls, and inter-agent communication. Howeve