Live intelligence

Latest AI updates

2 updates
Research

Depth as a Candidate Source: Portfolio Allocation for Recurrent Test-Time Scaling in Large Language Models

The paper analyzes recurrent latent reasoning in LLMs and finds that deeper recurrence can lose correct solutions found at shallower depths, with depth-specific success sets remaining broadly non-nested. It proposes Depth Portfolio Allocation (DPA), which treats recurrent test-time scaling as budgeted allocation across depth-specific candidate sources, supporting fixed and feedback-guided sequential allocation. Experiments on GSM8K, SVAMP, MultiArith, and MBPP indicate that mixed-depth portfolios expand oracle coverage under matched candidate counts and nominal costs, while feedback-guided allocation generally matches or improves uniform allocation and can reduce computation in high-budget settings.

test-time computeLLM reasoninginference efficiency
Research Editor selected

Test-Time Compute Scales Better with Parallel Agent Teams

The paper proposes parallel agent teams, a test-time scaling method that samples many small collaborating agent teams in parallel and keeps the best team's result. Evaluated on 12 long-horizon tasks spanning GPU kernels, formal proofs and exploit development, teams of ten with a 27B model and a 100-agent budget beat parallel independent agents on 10 of 12 tasks and beat a single team of 100 on all four tasks where such large teams were run. At equal dollar cost, the parallel teams beat a frontier model on half the tasks. A statistical model attributes the gains to balancing a higher mean with variance-based selection benefits.

Why it matters: It offers a concrete, empirically tested strategy for spending inference compute more effectively with multi-agent teams, relevant to practitioners scaling agent systems.

test-time computemulti-agent systemsinference scaling