Evaluating Memory Structure in LLM Agents
arXiv:2602.11243v2 Announce Type: replace-cross Abstract: Modern LLM-based agents and chat assistants rely on long-term memory frameworks to store reusable knowledge, recall user preferences, and augm
Knowledge catalogue
arXiv:2602.11243v2 Announce Type: replace-cross Abstract: Modern LLM-based agents and chat assistants rely on long-term memory frameworks to store reusable knowledge, recall user preferences, and augm
arXiv:2605.22897v1 Announce Type: new Abstract: A persistent challenge in machine learning for scientific applications is jointly achieving prediction and understanding. Statistical models excel on st
arXiv:2605.23754v1 Announce Type: new Abstract: Developing constitutive models that capture how materials deform under load traditionally requires years of specialized expertise in continuum mechanics
arXiv:2602.09851v2 Announce Type: replace Abstract: Feature Engineering (FE) is pivotal in automated machine learning (AutoML) but remains a bottleneck for traditional methods, which operate within ri
arXiv:2605.22613v1 Announce Type: new Abstract: Recent LLM-guided evolutionary search methods have shown that iterative program mutation can discover strong algorithms, but they typically optimize eac
arXiv:2605.22054v1 Announce Type: new Abstract: The high cost and data scarcity in scientific exploration have motivated the use of large language models (LLMs) as knowledge-driven components in Bayes
arXiv:2603.19310v3 Announce Type: replace Abstract: Reinforcement learning has emerged as a powerful paradigm for improving large language model (LLM) reasoning, where rollouts are sampled from the po
arXiv:2605.21082v1 Announce Type: new Abstract: Large Language Model (LLM) based agents have demonstrated proficiency in multi-step interactions with graphical user interfaces (GUIs). While most resea
arXiv:2605.22732v1 Announce Type: cross Abstract: We investigate whether acoustic emotion recognition models can serve as proxies for the Pathos dimension in political speech analysis, as operationali
arXiv:2603.27355v2 Announce Type: replace-cross Abstract: We present a readiness harness for LLM and RAG applications that turns evaluation into a deployment decision workflow. The system combines aut
arXiv:2605.20251v2 Announce Type: cross Abstract: Existing benchmarks for LLM coding agents primarily evaluate final outcomes. While useful for measuring overall capability, these metrics provide limi
arXiv:2605.22456v1 Announce Type: new Abstract: Cloud-hosted LLM driver agents provide useful semantic judgments, but their inference latency exceeds stepwise vehicle-control windows. Learned world mo
arXiv:2503.02885v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have gained traction in educational settings, often framed as virtual tutors or teaching assistants. Following ea
arXiv:2510.14444v3 Announce Type: replace Abstract: Post-training pruning can substantially reduce LLM inference costs, but it often degrades quality unless the remaining weights are adapted. Since gl
arXiv:2512.14896v2 Announce Type: replace Abstract: In our study, we evaluated large language model (LLM) performance on pharmacy licensure-style question-answering tasks and developed an external kno
arXiv:2605.21312v1 Announce Type: cross Abstract: Modern LLM serving is no longer homogeneous or monolithic. Production systems now combine disaggregated execution, complex parallelism, runtime optimi
arXiv:2603.06007v2 Announce Type: replace Abstract: Large language model-based (LLM-based) multi-agent systems (MAS) are increasingly used to extend agentic problem solving via role specialization and
arXiv:2605.19743v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly applied to engineering design tasks, yet existing evaluation frameworks do not adequately address mul
arXiv:2605.19529v1 Announce Type: new Abstract: When the same LLM generates assessment items, simulates student responses, and scores them, the validation loop is self-referential. We introduce Genera
It's been *almost* a bit quiet around LLM architecture releases in the past two weeks 😅 Interesting tidbit is the parallel block design. Via the Cmd-A the tech report 'equivalent performance but signi
arXiv:2605.18825v1 Announce Type: new Abstract: Prefix caching is a key optimization in Large Language Model (LLM) serving, reusing attention Key-Value (KV) states across requests with shared prompt p
arXiv:2605.18930v1 Announce Type: cross Abstract: Memory-augmented large language model (LLM) agents use iterative reflection and self-evolution to solve complex tasks, but these mechanisms introduce
arXiv:2605.18812v1 Announce Type: cross Abstract: Modern NLP and LLM systems are pipelines: named entity recognition (NER) -> entity disambiguation (NED) -> entity typing, retrieval-augmented generati
arXiv:2605.19932v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long and recurring external contexts, like document corpora and code repositories. Across in
arXiv:2605.19782v1 Announce Type: new Abstract: LLM discovery and optimization systems are increasingly applied across domains, implementing a common propose-evaluate-revise loop. Such optimization or
arXiv:2605.19952v1 Announce Type: new Abstract: To enable reliable long-term interaction, LLM agents require a memory system that can faithfully store, efficiently retrieve, and deeply reason over acc
arXiv:2605.19196v1 Announce Type: new Abstract: Deep research agents increasingly automate complex information-seeking tasks, producing evidence-grounded reports via multi-step reasoning, tool use, an
we've been building agents around the llm, starting with conversations, adding tools, giving rules, logging everything, and storing a form of it as retrievable state Active Graphs flips this. what if
arXiv:2605.16516v1 Announce Type: cross Abstract: Long-term interaction with LLM-based systems may produce alignment drift: a gradual process in which system outputs become less constrained by the use
arXiv:2605.17443v1 Announce Type: new Abstract: We analyze how automatic speech recognition (ASR) errors propagate through ASR-LLM cascades in Korean spoken question answering (SQA), focusing on downs
arXiv:2605.16309v1 Announce Type: new Abstract: LLM-based agents can recover from individual execution errors, yet they repeatedly fail on the same fault when the underlying process knowledge--operato
arXiv:2605.16386v1 Announce Type: new Abstract: Multimodal large language models (LLMs) are increasingly explored as automated evaluators in clinical settings, yet their scoring behavior on ordinal cl
arXiv:2604.04932v3 Announce Type: replace Abstract: The misuse of large language models (LLMs) requires precise detection of synthetic text. Existing works mainly follow binary or ternary classificati
arXiv:2602.16699v3 Announce Type: replace-cross Abstract: LLM agents are deployed in environments where they must interact to acquire information. In these scenarios, the agent must reason about inher
arXiv:2603.23638v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly tested on complex tasks, but their ability to allocate scarce resources over long horizons remain
arXiv:2605.17164v1 Announce Type: cross Abstract: Deploying large-scale LLM training and inference with optimal performance is exceptionally challenging due to a complex design space of parallelism st
arXiv:2605.16984v1 Announce Type: new Abstract: We present our submission to the LLM track of the 2026 Computational Models of Reference, Anaphora and Coreference (CRAC 2026) shared task. With an aver
arXiv:2511.20857v2 Announce Type: replace-cross Abstract: Statefulness is essential for large language model (LLM) agents to perform long-term planning and problem-solving. This makes memory a critica
arXiv:2605.16303v1 Announce Type: cross Abstract: Large language models (LLM) agents may offer tools to predict human responses to surveys. A common technique for defining these agents uses only demog
arXiv:2605.17734v1 Announce Type: new Abstract: Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizo
arXiv:2605.17106v1 Announce Type: new Abstract: Production LLM deployments increasingly maintain heterogeneous model pools spanning order-of-magnitude cost differences. Existing routers make binary st
arXiv:2603.00631v2 Announce Type: replace Abstract: LiTS is a modular Python framework for LLM reasoning via tree search. It decomposes tree search into three reusable components (Policy, Transition,
arXiv:2605.17292v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems have shown promise for solving complex tasks through agent collaboration. However, existing frameworks as
arXiv:2605.16895v1 Announce Type: cross Abstract: End-to-end LLM trading agents have moved quickly from research curiosity to a small ecosystem of named systems, including FinCon, FinMem, TradingAgent
arXiv:2605.17467v1 Announce Type: new Abstract: Large language model-driven multi-agent systems (LLM-MAS) excel at complex tasks, yet unreliable agents remain a key bottleneck to system-level reliabil
arXiv:2605.15617v1 Announce Type: cross Abstract: Large language model (LLM) training today runs on clusters spanning thousands of GPUs. While this scale enables rapid model advances, developing, debu
arXiv:2507.14200v2 Announce Type: replace-cross Abstract: Existing multi-LLM collaboration systems often encounter scalability challenges when integrating new LLMs and tasks, leading to suboptimal per
arXiv:2603.04459v3 Announce Type: replace-cross Abstract: The rapid expansion of research in LLM safety presents challenges in tracking advancements, making benchmarks important evaluation infrastruct
arXiv:2605.16205v1 Announce Type: new Abstract: Deploying compound LLM agents in adversarial, partially observable sequential environments requires navigating several design dimensions: (1) what the a
arXiv:2605.15412v1 Announce Type: cross Abstract: Modern quantitative trading increasingly relies on systematic models to extract predictive signals from large-scale financial data, where alpha factor
LLM apps fail in ways normal logs can’t explain. Same input, different outputs. Subtle drift. Silent hallucinations. That’s the problem space LangSmith by @LangChain was built for: observability + eva
arXiv:2605.16184v1 Announce Type: cross Abstract: Second-order methods offer an attractive path toward more sample-efficient LLM training, but their practical use is often blocked by the systems cost
🚨Breaking new study: memory in LLM agents still can’t really be trusted, even after over trillion dollars has gone into the development of the field. Excited to share our new paper: “Useful Memories B
arXiv:2605.14220v1 Announce Type: cross Abstract: Modern LLM RL systems separate rollout generation from policy optimization. These two stages are expected to produce token probabilities that match ex
arXiv:2602.02427v2 Announce Type: replace Abstract: Large language Models (LLMs) have achieved significant breakthroughs across diverse domains; however, they can still produce unreliable or misleadin
arXiv:2605.14249v1 Announce Type: new Abstract: We present EnergyLens, an end-to-end framework for energy-aware large language model (LLM) inference optimization. As LLMs scale, predicting and reducin
arXiv:2605.13941v1 Announce Type: cross Abstract: Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixe
arXiv:2605.13909v1 Announce Type: cross Abstract: Negotiation is a central mechanism of economic exchange, shaping markets, procurement, labor agreements, and resource allocation. It is also a canonic
arXiv:2605.12512v1 Announce Type: cross Abstract: Driven by large language models (LLMs), social bot can autonomously engage in local interactions, whose human-like behaviors enable them to evade soci
arXiv:2604.00001v2 Announce Type: replace-cross Abstract: Gradient-based data selection offers a principled framework for estimating sample utility in large language model (LLM) fine-tuning, but exist