arXiv AI
The belief-action gap in language model agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 1
When Should Models Change Their Minds? Contextual Belief Management in Large Language Models
arXiv:2605.30219v2 Announce Type: replace Abstract: Long-horizon interactions require language models to manage accumulating information: when to update their state, when to preserve their state, and...
arXiv AI
Jul 7
Ask the World Before Acting: Environment Probing for Calibrated Agent World Models
arXiv:2606. 31422v2 Announce Type: replace Abstract: Language agents acting over long horizons must maintain beliefs about tool states, object locations, graph edges, and subgoal dependencies.
arXiv AI
Jul 1
Ask the World Before Acting: Budgeted Environment Probing for World-Model Calibration
arXiv:2606. 31422v1 Announce Type: new Abstract: Long-horizon language agents do not only choose actions; they carry a private model of the world from one decision to the next.
arXiv AI
5d ago
Beyond Successful Play: Diagnosing Opponent Modeling in Large Language Models
arXiv:2610.17310v1 Announce Type: new Abstract: Language-model agents are expected to adapt to others whose behavior changes through interaction. Yet adaptation may rely on learned behavioral pattern...
arXiv AI
Oct 2
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States introduces PoS, an inference-time framework that builds and maintains explicit belief states to guide large language model agents. Each belief state combines an estimate of the current world with unresolved task requirements, making clear what the agent still needs to learn and accomplish. PoS validates consistency, monitors task progress to detect Belief Trapping, and tailors recovery to the trapping pattern and unresolved requirements, achieving top performance across four benchmarks with all three LLM backbones.
arXiv AI
Aug 26
MetaRAG: Belief-Action Aligned Policy Optimization for Agentic RAG
MetaRAG introduces a belief-action aligned policy optimization framework for agentic retrieval-augmented generation (RAG). It incorporates Verify-first Action Generation and Internal Belief Probing to assess whether the current evidence is sufficient before taking an action, and uses a consistency reward gated by answer correctness to guide training. Experiments on seven public QA benchmarks demonstrate that MetaRAG improves the accuracy-efficiency trade-off over existing RL-based agentic RAG baselines, with benefits that transfer across research settings, optimizers, and model backbones.