SimCT enlarges the supervision space in cross-tokenizer on-policy distillation using short jointly tokenizable multi-token continuations, producing consistent gains over shared-token baselines on math and code benchmarks.
Limi: Less is more for agency.arXiv preprint arXiv:2509.17567
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Multi-agent systems amplify minor stochastic biases into systemic polarization via echo-chamber effects in structured workflows, even with neutral agents.
AgencyBench is a new benchmark with 138 tasks in 32 scenarios that measures autonomous agent performance on extended real-world problems using simulated feedback and sandboxed assessment.
citing papers explorer
-
SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation
SimCT enlarges the supervision space in cross-tokenizer on-policy distillation using short jointly tokenizable multi-token continuations, producing consistent gains over shared-token baselines on math and code benchmarks.
-
Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems
Multi-agent systems amplify minor stochastic biases into systemic polarization via echo-chamber effects in structured workflows, even with neutral agents.
-
AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts
AgencyBench is a new benchmark with 138 tasks in 32 scenarios that measures autonomous agent performance on extended real-world problems using simulated feedback and sandboxed assessment.