12 posts published in the last hour
- 05:32Fault-Tolerant Budget Conservation in Distributed Multi-Agent Delegation
- 05:32Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts
- 05:32Mathematical Transfer in LLMs Follows Reasoning Approach More Than Topic
- 05:32OpenAI Releases GPT-6.1 Sol: Near-Astra Coding and Computer Use at One-Fifth of Astra’s Token Price
- 05:32ContractRL: Shielded Group-Relative Policy Optimization for Auditable Tool-Call Repair
- 05:32Google DeepMind Unveils Gemini 4 Argon with 1M Output Tokens for Coding, Knowledge Work and Cyber Defense
- 05:32Rules to Tools: Executable Checks for LLM Agents in Scientific Computing
- 05:02Robust Is Salient: An Informed Adversary Moves the Optimal Signal onto the Salience Pole
- 05:02Build2SPARQL: A Large-Scale Text-to-SPARQL Benchmark Dataset for Building Knowledge Graph Querying
- 05:02Knowing When to Yield: Grounded Arbitration of User Corrections in Text-Based Embodied Agents
- 05:02EviGraph: Proof-Carrying Selective Recommendation over Temporal Public-Service Knowledge Graphs
- 05:02Conflicting Supervision Moves Commitment, Not Capability: A 12.29{\sigma} arrangement effect that is exactly zero under a convention-agnostic score
