IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis
Ranking
Overall
81
Content
90
Popularity
60
Observed public metrics from 1 member.
Merged summary
TL;DR - IterSynth is a deep-search agent framework that separates planning from evidence synthesis and maintains a compact evolving summary instead of a growing search history. This reduces role coupling and context noise, improving long-horizon search performance across multiple models.
- Alternates between a Planner that identifies information needs and a Synthesizer that integrates evidence into the persistent summary state.
- Introduces Role-Decoupled Policy Optimization, combining terminal rewards, turn-level rubric evaluations, and role-specific advantage estimates.
- IterSynth-8B averages 50.7 across five deep-search benchmarks, outperforming the strongest prior agent at or below 8B parameters by 4.2%.
- The prompting paradigm also provides substantial reported zero-shot gains over ReAct-style approaches on frontier proprietary models.
Sources (1)
IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis
Public signals
Hugging Face upvotes 9
TL;DR - IterSynth is a deep-search agent framework that separates planning from evidence synthesis and maintains a compact evolving summary instead of a growing search history. This reduces role coupling and context noise, improving long-horizon search performance across multiple models.
- Alternates between a Planner that identifies information needs and a Synthesizer that integrates evidence into the persistent summary state.
- Introduces Role-Decoupled Policy Optimization, combining terminal rewards, turn-level rubric evaluations, and role-specific advantage estimates.
- IterSynth-8B averages 50.7 across five deep-search benchmarks, outperforming the strongest prior agent at or below 8B parameters by 4.2%.
- The prompting paradigm also provides substantial reported zero-shot gains over ReAct-style approaches on frontier proprietary models.