Paper Detail

Context-Aware RL for Agentic and Multimodal LLMs

Peiyang Xu, Bangzheng Li, Sijia Liu, Karthik R. Narasimhan, Pramod Viswanath, Prateek Mittal, Xingyu Fu

arxiv Score 24.3

Published 2026-06-15 · First seen 2026-06-16

General AI

Abstract

Large language models (LLMs) often fail when answering requires identifying a small but decisive piece of evidence within a long or complex context, such as a single line in a tool trace or a subtle detail in an image. We propose ContextRL, a context-aware reinforcement learning (RL) method that improves long-horizon reasoning and multimodal performance through an \emph{indirect} auxiliary objective. Instead of supervising only the final answer, ContextRL presents the model with a query, an answer, and two highly similar contexts, and rewards it for selecting the context that supports the query--answer pair, thereby encouraging fine-grained grounding. We construct contrastive context data in two domains: for coding agents, trajectories serve as contexts, yielding 1k pairs built via condition filtering; for multimodal reasoning, images serve as contexts, yielding 7K pairs built via generative editing and similarity search. ContextRL achieves average gains of +2.2% over standard GRPO on 5 long-horizon benchmarks, and +1.8% across 12 diverse visual question answering benchmarks. To disentangle the effect of the proposed objective from that of additional data, we compare against data-augmentation baselines that repurpose the same contrastive contexts as standard query--context--answer examples. These baselines provide little to no improvement, showing that the gains arise from the proposed context-selection objective rather than from the contrastive data alone.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{xu2026context,
  title = {Context-Aware RL for Agentic and Multimodal LLMs},
  author = {Peiyang Xu and Bangzheng Li and Sijia Liu and Karthik R. Narasimhan and Pramod Viswanath and Prateek Mittal and Xingyu Fu},
  year = {2026},
  abstract = {Large language models (LLMs) often fail when answering requires identifying a small but decisive piece of evidence within a long or complex context, such as a single line in a tool trace or a subtle detail in an image. We propose ContextRL, a context-aware reinforcement learning (RL) method that improves long-horizon reasoning and multimodal performance through an \textbackslash{}emph\{indirect\} auxiliary objective. Instead of supervising only the final answer, ContextRL presents the model with a query, an answ},
  url = {https://arxiv.org/abs/2606.17053},
  keywords = {cs.CL, cs.CV},
  eprint = {2606.17053},
  archiveprefix = {arXiv},
}

Metadata

{}