SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.13235 · 2026

Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains

Shuo Wang, Zhenghao Liu, Ge Yu, Yu Gu, Yukun Yan, Zulong Chen, Zhipeng Xu, Chunyi Peng, Yuqi Xiong

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 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/2602.13235.json · badge: /api/ran/2602.13235.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
NEUIR/Lang2Act community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_policy_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
NEUIR/Lang2Act/src/Easyr1/verl/trainer/core_algos.py
code served (permissive licence) · get_code("c4c4df4310b9d0a0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create a stand-in class for VF (VectorizedFunction or similar utility module)
class VF:
    @staticmethod
    def masked_mean(tensor, mask, dim=None, eps=1e-8):
        """Compute masked mean along specified dimension(s)."""
        if dim is None:
            # Reduce all dimensions
            masked = tensor * mask
            return masked.sum() / (mask.sum() + eps)
        else:
            # Reduce along specific dimension
            masked = tensor * mask
            return masked.sum(dim=dim) / (mask.sum(dim=dim) + eps)

# Monkey-patch VF into the module namespace for the functions to use
import sys
current_module = sys.modules[__name__]
setattr(current_module, 'VF', VF)

# Define small tensors for testing
batch_size = 2
response_length = 4

# Create tensors with distinct shapes for clarity
old_log_probs = torch.randn(batch_size, response_length)
log_probs = torch.randn(batch_size, response_length)
advantages = torch.randn(batch_size, response_length)
response_mask = torch.ones(batch_size, response_length)
response_mask[0, -1] = 0  # Mask out last token in first sequence

ARGS = {
    'old_log_probs': old_log_probs,
    'log_probs': log_probs,
    'advantages': advantages,
    'response_mask': response_mask,
    'clip_ratio_low': 0.2,
    'clip_ratio_high': 0.2,
    'clip_ratio_dual': 0.5,
    'loss_type': 'default',
    'loss_avg_mode': 'token',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
average_loss Not yet run
unverified (harvested, no recorded run)
NEUIR/Lang2Act/src/Easyr1/verl/trainer/core_algos.py
code served (permissive licence) · get_code("e27ac21db85182e7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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
average_loss
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2510.09285 (2025-10)
Spotlight on Token Perception for Multimodal Reinforcement Learning

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

Visual Retrieval-Augmented Generation (VRAG) enhances Vision-Language Models (VLMs) by incorporating external visual documents to address a given query. Existing VRAG frameworks usually depend on rigid, pre-defined external tools to extend the perceptual capabilities of VLMs, typically by explicitly separating visual perception from subsequent reasoning processes. However, this decoupled design can lead to unnecessary loss of visual information, particularly when image-based operations such as cropping are applied. In this paper, we propose Lang2Act, which enables fine-grained visual perception and reasoning through self-emergent linguistic toolchains. Rather than invoking fixed external engines, Lang2Act collects self-emergent actions as linguistic tools and leverages them to enhance the visual perception capabilities of VLMs. To support this mechanism, we design a two-stage Reinforcement Learning (RL)-based training framework. Specifically, the first stage optimizes VLMs to self-explore high-quality actions for constructing a reusable linguistic toolbox, and the second stage further optimizes VLMs to exploit these linguistic tools for downstream reasoning effectively. Experimental results demonstrate the effectiveness of Lang2Act in substantially enhancing the visual perception capabilities of VLMs, achieving performance improvements of over 4%. All code and data are available at https://github.com/NEUIR/Lang2Act.

For agents

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

get_harvested_code_for_paper("2602.13235")
get_code_for_paper("2602.13235")
have("2602.13235")

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

curl https://syntology.ai/api/ran/2602.13235.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.13235.svg)](https://syntology.ai/paper/2602.13235)

Connect an agent — have() is free.