Late but Valuable: Why Deadlines Change the Measured Value of LLM Reasoning
cs.LG, cs.AI, cs.DC
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- HiveMind: OS-Inspired Scheduling for Concurrent LLM Agent Workloads
- Shorter Reasoning, Earlier Answers? An Evaluation of Reasoning Interfaces
- Kairos: A Scalable Serving System for Physical AI
- Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments
- UniLabOS: An AI-Native Operating System for Autonomous Laboratories
- A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility
- Autellix: An Efficient Serving Engine for LLM Agents as General Programs
- CoAgent: Concurrency Control for Multi-Agent Systems
- Reasoning Models Can Be Effective Without Thinking
- Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows
- Faster Cascades via Speculative Decoding
- The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models
- Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs
- Real-Time Reasoning Agents in Evolving Environments
- Intelligence Under Time Constraints: Rethinking Test-Time Compute
- LAP: An Agent-to-Instrument Protocol for Autonomous Science
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis