SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.06700 · 2024

Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 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; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2402.06700.json · badge: /api/ran/2402.06700.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
morning9393/etpo canonical (classifier label)
classifier basis: census
6 ran · 3 no recorded run
FunctionStatusWhere it lives
check Ran
ran, honoured the contract we drafted
morning9393/etpo/etpo/utils/util.py
pointer only (licence: NONE) · get_code("1136e568a8e6dd2e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, morning9393/etpo 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_gard_norm Ran
ran, honoured the contract we drafted
morning9393/etpo/etpo/utils/util.py
pointer only (licence: NONE) · get_code("8da73b3ead760a3d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, morning9393/etpo 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.

huber_loss Ran
ran; our contract draft was wrong, not the code
morning9393/etpo/etpo/utils/util.py
pointer only (licence: NONE) · get_code("317a7486c52962a6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, morning9393/etpo 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.

precompute_freqs_cis Ran
ran, violated the contract we drafted
morning9393/etpo/etpo/models/codellama/model.py
pointer only (licence: NONE) · get_code("e93cc5b705c2eb3b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, morning9393/etpo 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.

reshape_for_broadcast Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
morning9393/etpo/etpo/models/codellama/model.py
pointer only (licence: NONE); the stored copy get_code serves, from alpha-vllm/llama2-accessory, is pointer only (licence: NOASSERTION) · get_code("70bf6ebaafd266c4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, morning9393/etpo 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.

sample_top_p Ran
ran; our contract draft was wrong, not the code
morning9393/etpo/etpo/models/codellama/generation.py
pointer only (licence: NONE); the stored copy get_code serves, from lichenghaobuaa/tokenlearning, is pointer only (licence: NONE) · get_code("8845976729f4c4ee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, morning9393/etpo 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.

apply_rotary_emb Not yet run
unverified (harvested, no recorded run)
morning9393/etpo/etpo/models/codellama/model.py
pointer only (licence: NONE) · get_code("ed8b68645cfd07e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, morning9393/etpo 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.

load_dataset Not yet run
unverified (harvested, no recorded run)
morning9393/etpo/etpo/envs/datascience/scikit_env.py
pointer only (licence: NONE) · get_code("e7a5d8632aa5c7dd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, morning9393/etpo 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.

load_kidney_stone Not yet run
unverified (harvested, no recorded run)
morning9393/etpo/etpo/envs/datascience/data_utils.py
pointer only (licence: NONE) · get_code("a67fe2b3be0765b7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, morning9393/etpo 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 4 later) and 4 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
reshape_for_broadcast 58 other papers
18 dated earlier, 4 the same month, 36 later · 2 only as an assembly brick
2023.emnlp-main.534 (2023 (year only))
Disentangling Transformer Language Models as Superposed Topic Models
2303.09736 (2023-03)
Dynamic Structure Pruning for Compressing CNNs
2307.09288 (2023-07)
Llama 2: Open Foundation and Fine-Tuned Chat Models
and 55 more not named here
sample_top_p 26 other papers
12 dated earlier, 13 later, 1 same year, order not determinable
2023.emnlp-main.534 (2023 (year only))
Disentangling Transformer Language Models as Superposed Topic Models
2305.08322 (2023-05)
C-EVAL: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models
2305.11554 (2023-05)
ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings
and 23 more not named here
precompute_freqs_cis 10 other papers
1 dated earlier, 9 later · 1 only as an assembly brick
2308.12950 (2023-08)
Code Llama: Open Foundation Models for Code
2408.01933 (2024-08)
DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models
2410.15495 (2024-10)
SEA: State-Exchange Attention for High-Fidelity Physics Based Transformers
and 7 more not named here
apply_rotary_emb 1 other paper
1 dated earlier
2308.12950 (2023-08)
Code Llama: Open Foundation Models for Code
huber_loss 1 other paper
1 later
2404.10740 (2024-04)
N-Agent Ad Hoc Teamwork

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

Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. Traditional approaches often depend on meticulously designed prompts, high-quality examples, or additional reward models for in-context learning, supervised fine-tuning, or RLHF. Reinforcement learning (RL) presents a dynamic alternative for LLMs to overcome these dependencies by engaging directly with task-specific environments. Nonetheless, it faces significant hurdles: 1) instability stemming from the exponentially vast action space requiring exploration; 2) challenges in assigning token-level credit based on action-level reward signals, resulting in discord between maximizing rewards and accurately modeling corpus data. In response to these challenges, we introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. At the heart of ETPO is our novel per-token soft Bellman update, designed to harmonize the RL process with the principles of language modeling. This methodology decomposes the Q-function update from a coarse action-level view to a more granular token-level perspective, backed by theoretical proof of optimization consistency. Crucially, this decomposition renders linear time complexity in action exploration. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks; results underline ETPO's potential as a robust method for refining the interactive decision-making capabilities of language agents. For a more detailed preliminary work describing our motivation for token-level decomposition and applying it in PPO methods, please refer to arXiv:2405.15821.

For agents

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

get_harvested_code_for_paper("2402.06700")
get_code_for_paper("2402.06700")
have("2402.06700")

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

curl https://syntology.ai/api/ran/2402.06700.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.06700.svg)](https://syntology.ai/paper/2402.06700)

Connect an agent — have() is free.