SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.04284 · ICML · 2026

Agent-Omit: Adaptive Context Omission for Efficient LLM Agents

Hao Liu, Jun Fang, Yansong Ning, Naiqiang Tan

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 4 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.04284.json · badge: /api/ran/2602.04284.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
usail-hkust/Agent-Omit canonical (classifier label)
classifier basis: census
6 ran · 4 no recorded run
FunctionStatusWhere it lives
collate_fn Ran
ran; our contract draft was wrong, not the code
usail-hkust/Agent-Omit/AgentOmit-RL/verl/utils/agent_dataset/rl_dataset.py
pointer only (licence: NONE) · get_code("ecd75498a47b0cf1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, usail-hkust/Agent-Omit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_to_regular_types Ran
ran; our contract draft was wrong, not the code
usail-hkust/Agent-Omit/AgentOmit-RL/verl/agent_trainer/fsdp_sft_trainer.py
pointer only (licence: NONE) · get_code("f887d72c9492d9ee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, usail-hkust/Agent-Omit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

discount_reward Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
usail-hkust/Agent-Omit/AgentOmit-Gym/agentenv/agentenv-webshop/webshop/baseline_models/agent.py
pointer only (licence: NONE) · get_code("6c873c43e9aed0a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, usail-hkust/Agent-Omit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_step Ran
ran, honoured the contract we drafted
usail-hkust/Agent-Omit/AgentOmit-RL/verl/agent_trainer/fsdp_sft_trainer.py
pointer only (licence: NONE) · get_code("216e28c040173a61")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, usail-hkust/Agent-Omit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_kl_controller Ran
ran; our contract draft was wrong, not the code
usail-hkust/Agent-Omit/AgentOmit-RL/verl/agent_trainer/ppo/core_algos.py
pointer only (licence: NONE) · get_code("45d08b3300b3da88")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, usail-hkust/Agent-Omit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_version Ran
ran; our contract draft was wrong, not the code
usail-hkust/Agent-Omit/AgentOmit-RL/verl/workers/agent_fsdp_workers.py
pointer only (licence: NONE) · get_code("fd54f6dcab409dca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, usail-hkust/Agent-Omit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_grpo_outcome_advantage Not yet run
unverified (harvested, no recorded run)
usail-hkust/Agent-Omit/AgentOmit-RL/verl/agent_trainer/ppo/core_algos.py
pointer only (licence: NONE) · get_code("9869c756ff538fd1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, usail-hkust/Agent-Omit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

create_device_mesh Not yet run
unverified (harvested, no recorded run)
usail-hkust/Agent-Omit/AgentOmit-RL/verl/workers/agent_fsdp_workers.py
pointer only (licence: NONE) · get_code("057fe261e2729ec3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, usail-hkust/Agent-Omit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

find_latest_ckpt_path_aistudio Not yet run
unverified (harvested, no recorded run)
usail-hkust/Agent-Omit/AgentOmit-RL/verl/agent_trainer/ppo/ray_trainer.py
pointer only (licence: NONE) · get_code("39da54e65be37106")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, usail-hkust/Agent-Omit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_sharding_strategy Not yet run
unverified (harvested, no recorded run)
usail-hkust/Agent-Omit/AgentOmit-RL/verl/workers/agent_fsdp_workers.py
pointer only (licence: NONE); the stored copy get_code serves, from xcyao00/HTPO, is pointer only (licence: NONE) · get_code("439358649f4873cc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, usail-hkust/Agent-Omit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 3 the same month, 3 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
extract_step 19 other papers
13 dated earlier, 3 the same month, 2 later, 1 undated
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
2502.14768 (2025-02)
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
and 16 more not named here
convert_to_regular_types 7 other papers
5 dated earlier, 2 the same month
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2504.05520 (2025-04)
Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
2505.04588 (2025-05)
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
and 4 more not named here
discount_reward 3 other papers
3 dated earlier
2207.01206 (2022-07)
WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
2306.02224 (2023-06)
Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions
2312.05742 (2023-12)
The Generalization Gap in Offline Reinforcement Learning
get_kl_controller 3 other papers
1 the same month, 2 later
2602.15564 (2026-02)
Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL
2606.07705 (2026-06)
SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models
2606.10646 (2026-06)
How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs
get_sharding_strategy 2 other papers
1 dated earlier, 1 later
2505.13417 (2025-05)
AdaptThink: Reasoning Models Can Learn When to Think
2605.08283 (2026-05)
HTPO: Towards Exploration-Exploitation Balanced Policy Optimization via Hierarchical Token-level Objective Control

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Managing agent context (e.g., thought and observation) during multi-turn agent-environment interactions is an emerging strategy to improve agent efficiency. However, existing studies treat the entire interaction trajectories equally, overlooking that the thought necessity and observation utility vary across turns. To this end, we first conduct quantitative investigations into how thought and observation affect agent effectiveness and efficiency. Based on our findings, we propose Agent-Omit, a unified training framework that empowers LLM agents to adaptively omit redundant thoughts and observations. Specifically, we first synthesize a small amount of coldstart data, including both single-turn and multiturn omission scenarios, to fine-tune the agent for omission behaviors. Furthermore, we introduce an omit-aware agentic reinforcement learning approach, incorporating a dual sampling mechanism and a tailored omission reward to incentivize the agent's adaptive omission capability. Theoretically, we prove that the deviation of our omission policy is upper-bounded by KL-divergence. Experimental results on five agent benchmarks show that our constructed Agent-Omit-8B could obtain performance comparable to seven frontier LLM agents, and achieve the best effectivenessefficiency trade-off among seven efficient LLM agent methods. Our code and data are available at https://github.com/usail-hkust/Agent-Omit.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.04284")
get_code_for_paper("2602.04284")
have("2602.04284")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.04284.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.04284.svg)](https://syntology.ai/paper/2602.04284)

Connect an agent — have() is free.