Post-cutoff performance decay has been widely interpreted as a temporal signal for benchmark contamination.We critically examine this belief and demonstrate that this temporal signal is highly sensitive to how benchmark questions are constructed.Specifically, we show that LLM-generated questions can produce remarkably different temporal patterns compared to fill-in-the-blank questions directly retrieved from the very same materials.We validated this finding on previous benchmarks that reported clear post-cutoff performance decay such as LiveCodeBench and further showed simple LLM transformation could effectively remove this temporal pattern when evaluated on the same models.We also provide a mechanistic understanding of our observation using influence function analysis.Overall, this work offers a new perspective on the sensitivity of temporal contamination signal and highlights the need for more robust contamination detection methods for reliable AI evaluation.

Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agents. However, whether LLM-based agents can reliably coordinate when each observes only a fragment of the global problem remains unclear. Existing benchmarks often prescribe agent roles or interaction patterns, conflating coordination ability with role-based priors. We introduce SILO-BENCH, a role-free benchmark for evaluating free-form collaboration under information silos. The benchmark comprises 30 algorithmic tasks with exact ground-truth answers, organized into 3 complexity levels based on optimal communication complexity: aggregation, mesh, and global shuffle. To systematically probe coordination capabilities, we instantiate 54 configurations by varying 3 communication protocols, 6 agent scales and 3 frontier LLMs, conducting 1,620 experiments. We evaluate agent behavior along three dimensions: Success Rate, Token Consumption, and Communication Density. Our experiments reveal a fundamental Communication-Reasoning Gap: agents communicate actively, yet fail to translate interaction into effective distributed computation. Performance collapses as complexity increases, with Level-III tasks achieving zero success beyond 50 agents. These findings demonstrate that current LLMs cannot escape information silos through coordination alone. SILO-BENCH provides a foundation for tracking progress toward genuinely collaborative multi-agent systems. The code is available at https://github.com/jwyjohn/acl26-silo-bench.

Current LLM-based multi-agent systems remain fragile under scaling, even on algorithmically trivial tasks. We introduce MAS-BENCH, a distributed-sorting benchmark that isolates coordination under explicit communication constraints: each agent observes only a local segment and must collectively produce a globally consistent order via broadcasting, peer-to-peer messaging, or a shared key-value store. Across LLM-based agents, success drops sharply as the number of agents grows, exposing persistent failures in shared state, convention alignment, and consistent termination. To mitigate these breakdowns, we propose CAMOC, a lightweight, drop-in proof-of-concept built on collaboration-aware information sharing, early global metadata exchange, and single-commit verification. CAMOC substantially improves coordination success and efficiency across backends, with the largest gains under shared-state interaction. Overall, MAS-BENCH provides a diagnostic benchmark and CAMOC offers a practical step toward more reliable large-scale LLM collaboration, highlighting a gap between individual reasoning and collective correctness.