Tool-use agents suffer large accuracy drops from reward and transition perturbations but domain-randomized RL on static perturbations closes about 27% of the unseen transition gap while retaining most clean performance.
Le, Christopher Ré, and Azalia Mirhoseini
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 4years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
PathCal calibrates reasoning paths by type-aware soft rebalancing of reflection-marker logits at uncertain states, yielding better efficiency-performance trade-offs on six benchmarks.
Verifier-backed committee search boosts a weak reasoning model from 67% to 76.4% on SWE-bench Verified, matching stronger models by using local soundness signals to select among proposals.
Squeeze Evolve is a multi-model orchestration framework that improves efficiency and performance in verifier-free evolutionary inference, cutting costs up to 3x while matching verifier-based methods on several benchmarks.
citing papers explorer
-
When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents
Tool-use agents suffer large accuracy drops from reward and transition perturbations but domain-randomized RL on static perturbations closes about 27% of the unseen transition gap while retaining most clean performance.
-
PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning
PathCal calibrates reasoning paths by type-aware soft rebalancing of reflection-marker logits at uncertain states, yielding better efficiency-performance trade-offs on six benchmarks.
-
Agentic Systems as Boosting Weak Reasoning Models
Verifier-backed committee search boosts a weak reasoning model from 67% to 76.4% on SWE-bench Verified, matching stronger models by using local soundness signals to select among proposals.
-
Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution
Squeeze Evolve is a multi-model orchestration framework that improves efficiency and performance in verifier-free evolutionary inference, cutting costs up to 3x while matching verifier-based methods on several benchmarks.