ECHO: Prune to act, trace to learn with selective turn memory in agentic RL

• URL: http://arxiv.org/abs/2606.31650v1
• Date: Tue, 30 Jun 2026 13:29:58 GMT
• Title: ECHO: Prune to act, trace to learn with selective turn memory in agentic RL
• Abstract summary: ECHO is a selective turn-memory framework that addresses history collapse and traceable learning through source-indexed reconstruction.<n>On BrowseComp-Plus, ECHO reaches 43.4% held-out accuracy, outperforming GRPO (28.9%) and the rolling-summary baseline SUPO (36.1%), while using fewer turns and lower trajectory volume than SUPO.
• Score: 9.429418772354397
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-horizon language agents must repeatedly interact with tools, accumulate evidence, and make decisions under bounded context windows. Existing context-management methods make such rollouts feasible by truncating distant history, folding past turns into summaries, or selecting compact memory states. However, these breakthroughs introduce two coupled limitations. First, as the number of turns grows, historical observations are progressively removed or collapsed into compressed states, making it harder for the policy to reuse fine-grained evidence. Second, once the original turns are no longer source-addressable, outcome-based RL loses an explicit path for aligning policy updates with the evidence that supported a successful final answer. To this end, we propose ECHO, a selective turn-memory framework that jointly addresses history collapse and traceable learning through source-indexed reconstruction. Specifically, ECHO compresses each completed environment turn into a compact memory record, reconstructs bounded policy contexts by selecting from these records, and reuses the selected source indices to route positive outcome credit to the evidence and selection actions that support successful answers. On BrowseComp-Plus, ECHO reaches 43.4% held-out accuracy, outperforming GRPO (28.9%) and the rolling-summary baseline SUPO (36.1%), while using fewer turns and lower trajectory volume than SUPO (Figure 1). Additionally, the trained policy improves zero-shot generalization across multi-objective QA, code generation, and deep information-seeking benchmarks on both dense and MoE backbones.

Related papers

• Harness-G: A Graph-Structured Harness for Search Agents [17.554676400013424]
  Reinforcement learning (RL) search agents commonly model retrieval as free-form natural-language query generation.<n>We propose Harness-G, a graph-structured retrieval framework that redesigns this interface.<n>It reformulates free-form query generation as finite action selection, while the environment constructs the menu, tracks retrieval state, and validates and executes each choice.<n>It achieves the highest average F1 at both evaluated model scales, outperforming the strongest baseline, Graph-R1, by 10.74 points at 1.5B and 3.98 points at 3B.
  arXiv  Detail & Related papers  (2026-07-30T04:05:05Z)
• SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning [14.505575259468053]
  Test-time reinforcement learning (TTRL) enables language models to self-evolve at inference time without labeled feedback.<n>We introduce SERPO, which replaces answer voting with a closed loop that co-evolves response evidence, querytokens, and policy parameters.<n>New actor rollouts then refresh both the archives and rubrics, closing the three-way evolution loop.
  arXiv  Detail & Related papers  (2026-07-29T13:03:07Z)
• ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning [78.94047086588078]
  We propose Recursive Evidence as LLM Harness for Long-Context Reasoning.<n>It is a training-free inference method for improving long-context reasoning.<n> Experiments on eight long-context datasets with 128K context length show it consistently improves evidence utilization.
  arXiv  Detail & Related papers  (2026-07-02T17:59:26Z)
• Same Ranking, Different Winner: How Scoring Targets Shape LLM Memory Benchmarks [2.9089118242427627]
  Conversational-memory systems transform dialogue history into facts, summaries, timelines, and other source-linked descendants.<n>This raises an underspecified evaluation question: which stored form should receive retrieval credit?<n>We show that this scoring-target choice is often left implicit and can materially change benchmark conclusions.
  arXiv  Detail & Related papers  (2026-05-22T02:53:07Z)
• RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation [14.301653810918713]
  Large Language Models (LLMs) have emerged as a promising paradigm for next-generation recommender systems.<n>We propose RRCM, a ranking-driven retrieval-and-reasoning framework for LLM-based agentic recommendation.
  arXiv  Detail & Related papers  (2026-05-08T02:07:30Z)
• Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS [5.711356514732554]
  Self-Correcting RAG reformulates retrieval and generation as constrained optimization and path planning.<n>On the input side, we formalize context selection as a multi-dimensional multiple-choice knapsack problem (MMKP)<n>On the output side, we introduce a natural language inference (NLI)-guided Monte Carlo Tree Search (MCTS) mechanism.
  arXiv  Detail & Related papers  (2026-04-12T17:14:36Z)
• Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval [59.295767860331004]
  RF-Mem is a familiarity uncertainty-guided dual-path memory retriever.<n>It embeds human-like dual-process recognition into the retriever.<n>It consistently outperforms one-shot retrieval and full-context reasoning under fixed budget and latency constraints.
  arXiv  Detail & Related papers  (2026-03-10T06:31:44Z)
• MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning [73.27233666920618]
  We propose MemSearcher, an agent workflow that iteratively maintains a compact memory and combines the current turn with it.<n>At each turn, MemSearcher fuses the user's question with the memory to generate reasoning traces, perform search actions, and update memory to retain only information essential for solving the task.<n>We introduce multi-context GRPO, an end-to-end RL framework that jointly optimize reasoning, search strategies, and memory management of MemSearcher Agents.
  arXiv  Detail & Related papers  (2025-11-04T18:27:39Z)
• Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization [56.97588709890706]
  LongMab-PO is a novel framework that generates high-quality and diverse responses for long-context modeling tasks.<n> Experimental results show that LongMab-PO significantly improves the diversity and quality of preference data pairs.
  arXiv  Detail & Related papers  (2025-08-19T16:33:55Z)
• Reinforcing Video Reasoning with Focused Thinking [65.85683941058916]
  We propose TW-GRPO, a novel framework that enhances visual reasoning with focused thinking and dense reward granularity.<n>Specifically, we employ a token weighting mechanism that prioritizes tokens with high informational density.<n>We also reformulate RL training by shifting from single-choice to multi-choice QA tasks.
  arXiv  Detail & Related papers  (2025-05-30T15:42:19Z)
• Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains [13.58151841630302]
  We propose a novel method METEORA that replaces re-ranking in RAG with a rationale-driven selection approach.<n>We show METEORA improves generation accuracy by 33.34% while using approximately 50% fewer chunks than state-of-the-art re-ranking methods.<n>In adversarial settings, METEORA significantly improves the F1 score from 0.10 to 0.44.
  arXiv  Detail & Related papers  (2025-05-21T20:57:16Z)
• Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization [95.85537087475882]
  Existing approaches underutilize the inherent knowledge of large language models (LLMs)<n>We propose Self-Routing RAG, a novel framework that binds selective retrieval with knowledge verbalization.<n> SR-RAG reduces the number of retrievals by 29% while improving performance by 5.1%.
  arXiv  Detail & Related papers  (2025-04-01T17:59:30Z)
• SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs [85.54906813106683]
  We propose a simple yet effective framework to enhance open-domain question answering (ODQA) with large language models (LLMs) SuRe helps LLMs predict more accurate answers for a given question, which are well-supported by the summarized retrieval (SuRe) Experimental results on diverse ODQA benchmarks demonstrate the superiority of SuRe, with improvements of up to 4.6% in exact match (EM) and 4.0% in F1 score over standard prompting approaches.
  arXiv  Detail & Related papers  (2024-04-17T01:15:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.