Qiming Shi, Yikun Li, Beidi Luan, Rui Sun, Sinuo Wang, Delin Wang, Yan Ma, Jing Li 等 10 位作者
Large language model (LLM) agents are extending agent-mediated commerce on the Web from shopping for consumers to operating businesses for sellers. In online-to-offline (O2O) commerce, decisions are issued through Web-based platforms but realized through costly physical execution. Evaluating such agents requires going beyond individual transactions to ask whether decisions made online turn into sustained economic returns. We introduce AutoVend, a benchmark in which one LLM agent manages 20 vending machines across five site types through a Web-based operating interface for 180 simulated days. Its data-grounded simulator combines a shared warehouse, procurement lead times, paid replenishment, inventory expiration, and recurring operating costs. We evaluate five LLM agents against a rule-based inventory-control baseline and diagnose their site coordination, execution, and performance over time. Four of five evaluated LLM agents fall short of this baseline, and returns per dollar of inference cost rank models differently from returns alone. Operational analyses show that gains in individual metrics do not consistently yield stronger economic growth, as inventory and execution costs erode these gains. Trajectory analysis further reveals difficulties in grounding feasible actions, managing inventory commitments, and converting feedback into effective policy revisions.
Mohammad Javad Amiri, Carsten Binnig, Andreas Kipf, Tim Kraska, Ryan Marcus, Johannes Wehrstein, Chenyuan Wu, Geoffrey X. Yu 等 9 位作者
For the first time in history, high-performance code is cheap. Today's coding agents can generate bespoke, instance-optimized data systems with excellent performance, and such agents will continue to improve as LLMs advance. But a purely agentic approach, even when validated with strong testing techniques, does not automatically inherit the correctness guarantees our community has spent decades building. We propose a middle ground between hand-crafted and agent-crafted systems: correctness firewalls, lightweight design patterns under which a synthesized component can affect a system's performance but never its results. Behind a correctness firewall, agents are free to synthesize fast components while the overall system remains correct. We present three case studies, each demonstrating a different type of firewall: cardinality estimation (advisory), searching sorted data (guarded), and data compression (certified). In early experiments, synthesized components search sorted data up to 3x faster than human-designed learned indexes and can compress text 1.5x smaller than Zstd. Drawing on these case studies, we outline a research agenda for how data management systems can exploit coding agents without giving up their hard-won correctness guarantees, from protecting synthesized code to measuring the cost of correctness.
José Oliveira, Pedro Valente, Tiago Mendes, André Vasconcelos, Tiago Fernandes, Rhyan Matos, Duarte Raposo, Pedro Rito 等 10 位作者
During disasters, public mobile networks may become unavailable, congested, or degraded, requiring deployable communication systems to support emergency operations. This article proposes a mission-critical communications system supporing Mission Critical Push-to-Talk (MCPTT), Mission Critical Video (MCVideo), and Mission Critical Data (MCData) over a private 5G standalone network with Non-Terrestrial Network (NTN) connectivity. A context-aware Quality, Priority, and Pre-emption (QPP) mechanism is proposed to dynamically adapt network resource allocation according to the operational state of Mission Critical Services (MCX). Extensions to the Open5GS Policy Control Function (PCF) and Session Management Function (SMF) enable priority and pre-emption updates for existing flows without session re-establishment. The architecture supports tactical edge deployment of service and media functions while retaining centralized service control. Experimental evaluation considers three configurations: terrestrial backhaul with centralized media processing, satellite backhaul with centralized media processing, and satellite backhaul with edge media processing. Results show that tactical edge processing reduces communication delay and packet loss. Under satellite backhaul, edge processing reduced the 95th-percentile MCPTT audio transport delay by 60.03 ms and packet loss by 9.42 percentage points, while achieving a 95th-percentile MCPTT access time of 184.52 ms. These findings demonstrate the benefits of tactical edge media processing and provide an experimental foundation for context-aware priority mechanisms in public-safety networks integrating terrestrial and non-terrestrial components.
A memory can be outdated for present-day reasoning yet indispensable for reconstructing the past. Relevance-based retrieval overlooks this tension: semantic relevance, evidence-grounded validity, and query-specific eligibility are distinct. We propose CALM, a conflict-aware lifecycle memory governance framework that decouples persistent memory preservation from query-time admission. CALM converts heterogeneous records into evidence-grounded memory cells, updates validity and lifecycle states using support, conflict, and dependency signals, and admits query-appropriate evidence through training-free or learned gating informed by temporal applicability. Across LongMemEval-S and LoCoMo with Qwen and GPT backbones, CALM outperforms state-of-the-art baselines, achieving the best overall accuracy. Compared with simple filtering and reranking, query-conditioned admission further improves evidence selection. Conflict-blocking and robustness analyses show CALM suppresses erroneous retrieved memories while retaining useful evidence. Historical-reconstruction experiments demonstrate that preserving superseded records supports accurate earlier-state reasoning without compromising current-state answers.
Runxuan Liu, Xianhao Ou Harbin Institute of Technology, Xinyan Ma Harbin Institute of Technology, Jiyuan Wang, Jiafeng Liang Harbin Institute of Technology, Jiaqi Li Tianjin Normal University, Tao He Harbin Institute of Technology, Zheng Chu Harbin Institute of Technology 等 16 位作者
Long Chain-of-Thought (LCoT), achieved by Reinforcement Learning with Verifiable Rewards (RLVR), has proven effective in enhancing the reasoning capabilities of Large Language Models (LLMs). However, reasoning in current LLMs is primarily generated as plain text, where performing semantic evaluation on such unstructured data creates a computational bottleneck during training. Despite RLVR-based optimization, existing methods still suffer from coarse-grained supervision, reward hacking, high training costs, and poor generalization.To address these issues, we propose the Graph Reasoning Paradigm (GRP), which realizes structured and symbolic reasoning, implemented via graph-structured representations with step-level cognitive labels. Building upon GRP, we further design Process-Aware Stratified Clipping Group Relative Policy Optimization (PASC-GRPO), which leverages structured evaluation to replace semantic evaluation, achieves process-aware verification through graph-structured outcome rewards, and mitigates reward hacking via stratified clipping advantage estimation. Experiments demonstrate significant improvements across mathematical reasoning and code generation tasks. Data, models, and code will be released later.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表