TRACER: Per-Tool Context Retention for LLM Agents via Consequence-Attributed Reinforcement Learning

• URL: http://arxiv.org/abs/2608.29363v1
• Date: Sat, 29 Aug 2026 16:50:44 GMT
• Title: TRACER: Per-Tool Context Retention for LLM Agents via Consequence-Attributed Reinforcement Learning
• Abstract summary: Existing compression strategies allocate retention budgets without accounting for the downstream consequences of removing individual tool outputs.<n>We propose TRACER, which formulates compression as a sequential per-tool decision problem.
• Score: 8.886237275784852
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Enterprise data agents answer business queries by chaining many tool calls over multiple reasoning steps, routinely accumulating hundreds of thousands of context tokens per session. Existing compression strategies typically allocate retention budgets without accounting for the downstream consequences of removing individual tool outputs. Aggressive compression may therefore trigger costly tool re-invocations that offset the initial savings. We call this the compression--consequence gap. To close it, we propose TRACER, which formulates compression as a sequential per-tool decision problem. A lightweight REINFORCE policy assigns query-conditioned retention ratios using only information available at each compression event. Its consequence-aware objective jointly accounts for task success, total token consumption, and post-compression tool re-invocations. To improve credit assignment, TRACER uses a learned outcome model to compare the predicted consequences of the selected retention ratio with those of fully retaining each tool output. On held-out production queries across three compressor backends, TRACER reduces total token consumption by 29--46% relative to keeping all context while maintaining comparable or higher task success. Compared with a tool-type-conditional static policy, TRACER provides an additional 15--18% of token savings. Interventional rollouts show that the learned per-tool credit scores correlate with measured single-tool consequences. The learned policy also yields positive savings when transferred across agent backbones and compressor architectures, and reduces token consumption by 18--25% on five held-out LOCA-bench environments. These results demonstrate the value of consequence-aware, per-tool context retention for improving the efficiency of long-horizon language agents.

Related papers

• CoACT: Action-Preserving Observation Compression for Coding Agents [8.484842324052751]
  This paper proposes CoACT, an action-preserving observation compression method for coding agents.<n>CoACT is built on next-action preservation (NAP), which requires a compressed observation to induce the same next action as the raw observation.<n> Experiments on SWE-bench Verified with three agentic models show that CoACT reduces average total token consumption by 33.0%.
  arXiv  Detail & Related papers  (2026-07-03T03:17:52Z)
• Notation Matters: A Benchmark Study of Token-Optimized Formats in Agentic AI Systems [0.0]
  Large language models in Agentic AI systems consume tool schemas and execution results as structured data.<n>Recent work proposes token-optimized alternatives such as TOON (Token-Oriented Object Notation) and TRON (Token Reduced Object Notation) as more compact replacements.<n>We evaluate TOON and TRON on four agentic benchmarks (BFCL, MCPBenchPP, MCP-Universe, StableTool) and five open-weight LLMs.
  arXiv  Detail & Related papers  (2026-05-28T09:38:13Z)
• On the Effectiveness of Context Compression for Repository-Level Tasks: An Empirical Investigation [22.803236151303846]
  Repository-level code intelligence tasks require large language models to process long, multi-file contexts.<n> Context compression mitigates these risks by condensing inputs.<n>We present the first systematic empirical study of context compression for repository-level code intelligence.
  arXiv  Detail & Related papers  (2026-04-15T11:00:17Z)
• Arbitrary Ratio Feature Compression via Next Token Prediction [52.10426317889982]
  Arbitrary Ratio Feature Compression (ARFC) framework supports any compression ratio with a single model.<n>ARC is an auto-regressive model that performs compression via next-gressive prediction.<n>MoS module refines the compressed tokens by utilizing multiple compression results.<n>ERGC is integrated into the training process to preserve semantic and structural relationships during compression.
  arXiv  Detail & Related papers  (2026-02-12T02:38:57Z)
• AgentOCR: Reimagining Agent History via Optical Self-Compression [25.87457777208574]
  We introduce AgentOCR, a framework that exploits the superior information density of visual tokens.<n>By decomposing history into hashable segments and maintaining a visual cache, AgentOCR eliminates redundant re-rendering.<n>Results demonstrate that AgentOCR preserves over 95% of text-based agent performance while substantially reducing token consumption.
  arXiv  Detail & Related papers  (2026-01-08T10:10:20Z)
• VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs [82.72388893596555]
  Multimodal Large Language Models (MLLMs) encounter significant computational and memory bottlenecks.<n>Previous token compression techniques are often constrained by rules that risk discarding critical information.<n>We reformulate token compression as a lightweight plug-and-play framework that reformulates token compression into an end-to-end learnable decision process.
  arXiv  Detail & Related papers  (2025-10-18T17:54:18Z)
• Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning [71.30276778807068]
  We propose a unified framework that strategically coordinates sample pruning and token pruning.<n>Q-Tuning achieves a +38% average improvement over the full-data SFT baseline using only 12.5% of the original training data.
  arXiv  Detail & Related papers  (2025-09-28T13:27:38Z)
• ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models [62.82372407840088]
  Large language models (LLMs) transcend passive generation and act as goal-directed agents by invoking external tools.<n>textbfReshaped textbfToken-level policy gradients (textbfResT) for tool-use tasks.<n>textbfResT achieves state-of-the-art results, outperforming prior methods by up to $8.76%$.
  arXiv  Detail & Related papers  (2025-09-26T03:38:27Z)
• CORE-RAG: Lossless Compression for Retrieval-Augmented LLMs via Reinforcement Learning [22.93037884068796]
  Retrieval-Augmented Generation (RAG) has emerged as a promising approach to enhance the timeliness of knowledge updates and the factual accuracy of responses in large language models.<n>Existing approaches to document compression tailored for RAG often degrade task performance.<n>We propose CORE, a novel method for lossless context compression in RAG.
  arXiv  Detail & Related papers  (2025-08-24T12:21:50Z)
• Efficient Token Compression for Vision Transformer with Spatial Information Preserved [59.79302182800274]
  Token compression is essential for reducing the computational and memory requirements of transformer models.<n>We propose an efficient and hardware-compatible token compression method called Prune and Merge.
  arXiv  Detail & Related papers  (2025-03-30T14:23:18Z)
• Concise and Precise Context Compression for Tool-Using Language Models [60.606281074373136]
  We propose two strategies for compressing tool documentation into concise and precise summary sequences for tool-using language models. Results on API-Bank and APIBench show that our approach reaches a performance comparable to the upper-bound baseline under up to 16x compression ratio.
  arXiv  Detail & Related papers  (2024-07-02T08:17:00Z)

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.