arXiv AI
Aug 11
Business Arena: Benchmarking LLM Agents in a Realistic Marketplace
arXiv:2608. 08621v1 Announce Type: new Abstract: Running a business is a challenging form of intelligent work.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Aug 11
The Scaffolding Matters More Than the Interface: A Controlled Comparison of MCP and CLI Tool Use Across Seven Agent Scaffoldings, Five Language Models, and One Software Task
arXiv:2608. 08654v1 Announce Type: new Abstract: How much an AI coding agent costs to run can depend more on the agent scaffolding that drives it than on the interface through which it reaches its tools.
arXiv AI
Aug 11
PluginEval: A Diagnostic Benchmark for Fine-Grained Error Attribution in Function Calling
arXiv:2608. 08700v1 Announce Type: new Abstract: Reliable evaluation of tool routing is critical as Large Language Models increasingly operate as autonomous agents.
arXiv AI
Aug 11
SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification
arXiv:2608. 08786v1 Announce Type: new Abstract: Large language models (LLMs) increasingly serve as data-driven reasoners, yet their chains-of-thought (CoT) can be unfaithful even when final answers are correct.
arXiv AI
Aug 11
Improving Generalization Robustness of Multimodal RLVR
arXiv:2608. 08802v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) makes Multimodal Large Language Models more accurate, but the gains are brittle: simply paraphrasing a question or changing the prompt template can degrade them, which challenges reliable deployment in high-stakes scenarios like medical VQA.
arXiv AI
Aug 11
Automated Generation of Complexity-Validated Decision Scenarios Using Large Language Models
arXiv:2608. 08822v1 Announce Type: new Abstract: Cognitive decision-making research depends on diverse scenarios with carefully controlled complexity, yet manual production is slow, inconsistent, and biased.
arXiv AI
Aug 11
LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing
arXiv:2608. 08889v1 Announce Type: new Abstract: Recommendation systems thrive on personalization, where ''correctness'' is rarely a binary truth but a matter of subjective human preference.
arXiv AI
Aug 11
Integrated Multimodal AI System for Retrieval-Augmented Reasoning, Object Sensing, and Damage Analysis
arXiv:2608. 08935v1 Announce Type: new Abstract: This work presents a unified multimodal AI system for damage assessment that integrates retrieval-augmented generation (RAG) models, thermal spectrum perception, vision foundation model pipelines, and exploratory wireless signal sensing.
arXiv AI
Aug 11
PolicyKG: An Agentic LLM Pipeline for Translating Institutional Policies into SHACL Knowledge Graphs
arXiv:2608. 09028v1 Announce Type: new Abstract: Institutional policies stay in natural language while the systems that check compliance demand machine-readable constraints.
arXiv AI
Aug 11
RISE-RL: Rubric-Informed Selective Exploration for Open-Ended Reinforcement Learning
arXiv:2608. 09123v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) for open-ended tasks is challenging because responses must satisfy multidimensional criteria without following a single correct generation trajectory.
arXiv AI
Aug 11
Omni2LoRA: Coherence-Preserving Parametric Memory for Efficient Omni Language Models
arXiv:2608. 09227v1 Announce Type: new Abstract: Omnimodal language models (OLMs) enable unified audio-visual understanding, but processing long joint token sequences makes inference computationally prohibitive.
arXiv AI
Aug 11
Emotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolution
arXiv:2608. 09248v1 Announce Type: new Abstract: Skill-based LLM agents select reusable procedures from an external library to solve complex tasks, yet their routing decisions rely entirely on text-level signals such as task descriptions, verbal reflections, and experience-derived rules, while the model's own internal representational state remains unobserved.
arXiv AI
Aug 11
MMArch: Benchmarking Multimodal Reasoning Grounded in Architectural Evidence
arXiv:2608. 09281v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) perform strongly on engineering imagery, yet existing benchmarks mostly test drawing recognition, information extraction, or compliance checking, leaving open whether models can combine distributed visual evidence with engineering principles to reach a conclusion.
arXiv AI
Aug 11
LLM-Guided Heuristic Design from Simulation Traces: A Case Study in Dynamic Production and AGV Scheduling
arXiv:2608. 09343v1 Announce Type: new Abstract: Simulation-based optimization (SBO) evaluates executable policies under stochastic dynamics, but most methods treat the simulator as a black box: aggregate scores rank candidates without revealing why they fail or which policy logic should change.
arXiv AI
Aug 11
CircuitReason-1k: Benchmarking Long-Horizon Visual-to-Symbolic Reasoning inElectrical Circuits
arXiv:2608. 09374v1 Announce Type: new Abstract: Electrical circuit analysis requires more than recognizing components in an image.
arXiv AI
Aug 11
OpenLoopEvolve: A Verifiable Self-Evolution Framework for Loop Policies in Long-Horizon Complex Tasks
arXiv:2608. 09380v1 Announce Type: new Abstract: Long-horizon complex tasks require agents to repeatedly observe states, formulate plans, invoke tools, verify results, and recover from failures in continuously changing environments.
arXiv AI
Aug 11
KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models
arXiv:2608. 09412v1 Announce Type: new Abstract: KV-cache compression reduces long-context memory, but aggregate task scores reveal neither which correct executions fail nor why.
arXiv AI
Aug 11
Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines?
arXiv:2608. 09629v1 Announce Type: new Abstract: Self-evolving agents are usually built around prescribed optimization pipelines: the framework decides how to gather evidence, revise a persistent artifact, select candidates, and stop.
arXiv AI
Aug 11
Avalon-ToM-Bench: Evaluating Fine-Grained Theory of Mind via Asymmetric Game Mechanics
arXiv:2608. 09638v1 Announce Type: new Abstract: Theory of Mind (ToM) is essential for agent interactions, yet existing evaluations either rely on static scenarios that oversimplify mental-state reasoning or interactive settings that provide limited diagnostic insight.
arXiv AI
Aug 11
Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
arXiv:2608. 09696v1 Announce Type: new Abstract: Predicting the answer to interventional ``what if'' questions --- the outcome of an action never taken --- requires a \emph{mechanistic}, causal model, not a curve fit; and learning such a model requires \emph{experiments}, because passive data leaves its mechanisms unidentified.