1
涉及应用适配：华为鸿蒙 HarmonyOS 7 系统沉浸光感新增生效约束
IT之家 9 月 3 日消息，华为开发者官网 OS 平台行为变更说明今日迎来更新， 宣布沉浸光感新增生效约束 。针对此次变更，华为官方也给出了原因和影响： 变更原因： 为确保性能和功耗体验最优，规范沉浸光感组件使用，沉浸光感对部分组件新增生效范围的约束。 变更影响： 此变更涉及应用适配（此变更涉及的…
2
Do Not Copy/Paste: Soft Barriers for Copying in AI-Assisted Programming
揭秘AI辅助编程中的复制粘贴软屏障，为开发者提供防误操作的协作新思路
arXiv:2608.22638v1 Announce Type: cross Abstract: Copying a function from a chat window into an editor takes less than a second. For many uses of AI c…
3
Encoded but Not Actionable: Auditing the Decode-Generate-Steer Gap in Frozen LLMs for Geometric Constraints
冻结大模型能“看懂”几何约束却不会用，审计揭示解码-生成-引导三环断裂，值得关注。
arXiv:2608.17843v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong performance on structured reasoning tasks, but…
4
CAPO: Constraint-Aware Prompt Optimization for LLM Agents
针对LLM智能体的提示词优化新方法，把约束条件纳入优化过程，让Agent更懂规则、少犯错。
arXiv:2608.16068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that rely on system prompts to use …
5
Constraint-Aware Synthetic Tabular Data Generation via Inter-Column Constraint Discovery with LLM Agents
用LLM智能体自动发现列间约束，让合成表格数据更真实可信，为数据增强与隐私保护提供新思路。
arXiv:2608.15109v1 Announce Type: new Abstract: Generating structurally valid synthetic tabular data remains difficult: outputs with high statistical …
6
LLMs Know the Constraint But Do Not Use It: Activation Bottlenecks in Pragmatic Constraint Reasoning
大模型知道规则却不会用？这篇论文揭示激活瓶颈如何阻碍实用约束推理，对理解LLM推理机制很有价值。
arXiv:2608.12321v1 Announce Type: cross Abstract: When a salient surface cue competes with an implicit feasibility constraint, LLMs often fail -- but …
7
Show HN: Fail the Build on Direct Service Calls
用构建失败强制服务隔离，杜绝越层调用，守护微服务架构边界。
Article URL: https://github.com/vijayagopalsb/isolation-tax Comments URL: https://news.ycombinator.com/item?id=49296427 Points: 1 # Comments: 0
8
Lost in Compaction: Evaluating Side-Constraint Loss under Context Compaction
当上下文被压缩，模型还能守住约束吗？这篇论文系统评估“侧约束损失”，揭示压缩带来的隐藏风险。
arXiv:2608.11242v1 Announce Type: cross Abstract: When the context window is under pressure, LLM systems compact prior context to continue ongoing tas…
9
UNSPECIFIC: General Constraint Synthesis for Breaking Copy-and-Paste Shortcut in LLM Instruction Following
破解大模型指令遵循中的复制粘贴捷径，用通用约束合成让模型真正理解复杂指令，AI训练方法论新突破
arXiv:2608.09154v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly expected to follow long lists of constraints in complex …
10
ComboShoppingBench: Evaluating LLM Agents for Budget-Constrained Basket Shopping with Coupons
LLM智能体在预算约束与优惠券组合购物中表现如何？全新基准ComboShoppingBench给出量化答案
arXiv:2608.09282v1 Announce Type: new Abstract: Real-world shopping often requires constructing a basket of complementary items rather than retrieving…
11
Stateful CARS: Exact Cross-History Reuse for Policy-Constrained LLM Agents
LLM代理的跨历史缓存复用新方案，精确匹配策略约束，大幅提升推理效率。
arXiv:2608.08282v1 Announce Type: new Abstract: Tool-using language-model agents face constraints whose meaning changes with observations and prior ac…
12
Improving Constraint Models with LLM Agents
用LLM代理自动优化约束编程模型，突破传统人工调参瓶颈，让求解器性能跃升。
arXiv:2608.08127v1 Announce Type: new Abstract: The runtime of Constraint Programming (CP) solvers is highly sensitive to modeling choices, such as sy…
13
Does Splitting a Triage Decision Across Agents Hide Bias or Help Catch It? A Multi-Agent Simulation Study of LLM-Based Resource Allocation Under Audit Capacity Constraints
多智能体拆分分诊决策，能否在审计受限时揪出偏见？模拟研究揭示真实部署中的隐藏风险。
arXiv:2608.06949v1 Announce Type: new Abstract: Prior benchmarking work has shown that a single large language model (LLM), forced to make life-or-dea…
14
EcoAgent-Bench: Evaluating Economic Decision-Making in Budget-Constrained LLM Agents
评估LLM代理在预算约束下的经济决策，揭示资源效率与任务完成度的平衡新基准。
arXiv:2608.05519v1 Announce Type: new Abstract: Agent benchmarks usually measure task completion and treat resource use as an auxiliary statistic. In …
15
Semantic Thermodynamics – 79% LLM token reduction via narrative constraints
用叙事约束为 LLM 减负：token 消耗降低 79%，系统延迟从 3.4s 降到 1.3s，语义热力学带来全新优化视角。
Article URL: https://github.com/tauansloboda/semantic-thermodynamics Comments URL: https://news.ycombinator.com/item?id=49190710 Points: 2 # Comments:…
16
Suffix-Constrained Greedy Search Algorithms for Causal Language Models
给大模型生成加上指定结尾的贪心解码新方法，提升输出可控性。
arXiv:2603.01243v2 Announce Type: replace Abstract: Large language models (LLMs) are powerful tools that have found applications beyond human-machine …
17
SCHEDBench: A Benchmark for Evaluating LLM Constraint Faithfulness in Natural-Language Combinatorial Scheduling
全新基准SCHEDBench，专测大模型在自然语言组合调度中的约束遵循能力。
arXiv:2608.00991v1 Announce Type: new Abstract: This paper introduces SCHEDBench, a natural-language benchmark for evaluating combinatorial scheduling…
18
Optimization and Constraint Modeling using LLMs with a Retrieval Augmented Generation Process
用检索增强生成驱动大模型，破解复杂约束建模与优化难题，工程实践必读。
arXiv:2608.00015v1 Announce Type: new Abstract: Both optimization modeling and constraint modeling are non-trivial problems requiring deep domain expe…
19
合规约束叠加海外壁垒，“新三样”ESG竞争力加速兑现
A股ESG强制信披规则实施，叠加海外市场对进口产品设置严苛绿色准入门槛，倒逼“新三样”企业深化ESG合规管理、提质升级，整体成效显著。截至8月2日，新能源汽车、锂电池、光伏产业上市公司2025年度ESG报告披露率高于A股市场平均披露率，A级及以上高评级企业占比大幅领先市场整体水平。龙头公司通过持续完…
20
LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints
多约束指令总翻车？DeCRIM用分解-批判-修正三步，让LLM自我纠错能力显著提升。
arXiv:2410.06458v2 Announce Type: replace-cross Abstract: Instruction following is a key capability for LLMs. However, recent studies have shown that …