re-trac-trajectory-compression

name	re-trac-trajectory-compression
title	RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents
version	0.0.2
engine	skillxiv-v0.0.2-claude-opus-4.6
license	MIT
url	https://arxiv.org/abs/2602.02486
keywords	["Search Agents","Trajectory Compression","Recursive Planning","Evidence Tracking"]
description	Compress search trajectories into structured states capturing partial answers, evidence, and uncertainties. Recursive execution leverages compressed states to avoid redundant exploration, improving resource efficiency by 50%.

RE-TRAC: Recursive Trajectory Compression for Search

Problem

ReAct-style search agents suffer from incomplete branch exploration—up to 93% of planned branches never execute due to linear trajectory structure. Independent parallel attempts (Pass@k scaling) miss cross-trajectory learning.

Long sequences consume tokens and computational resources. Agents need structured, compressible representations of search progress.

Core Concept

RE-TRAC compresses search trajectories into structured state representations capturing answer progress, evidence base, and unresolved questions. These compressed states seed the next search round, enabling targeted exploration of incomplete branches.

Recursive execution with cross-trajectory learning reduces resource consumption while improving final performance.

Architecture Overview

• Structured State Representation: Answer & Conclusions, Evidence Base, Uncertainties
• Evidence Tracking: Source verification and provenance for all claims
• Recursive Execution: Use compressed states as input for continuation rounds
• Branch Exploration: Systematically address unresolved questions from previous round
• Resource Monitoring: Track cumulative computation across rounds

Implementation

Step 1: Define Structured State Representation

Create compress format for search progress.

class StructuredSearchState:
    def __init__(self):
        self.partial_answers = []  # Best-supported answers found so far
        self.evidence_base = []    # All discovered evidence with sources
        self.uncertainties = []    # Open questions needing exploration

    def add_partial_answer(self, answer_text, confidence, supporting_evidence):
        """Record a potential answer with its support."""
        self.partial_answers.append({
            'text': answer_text,
            : confidence,
            : supporting_evidence
        })

     ():
        
        .evidence_base.append({
            : claim,
            : source_url,
            : verification_status,
            : datetime.now().isoformat()
        })

     ():
        
        .uncertainties.append({
            : question,
            : reason,
            : next_steps
        })

     ():
        
        prompt = 

         .partial_answers:
            prompt += 
            sorted_answers = (.partial_answers, key= x: x[], reverse=)
             ans  sorted_answers[:]:
                prompt += 

         .evidence_base:
            prompt += 
             ev  .evidence_base[:]:
                status =   ev[]  
                prompt += 

         .uncertainties:
            prompt += 
             unc  .uncertainties:
                prompt += 
                prompt += 

         prompt